Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Disproven/rejected ideas

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens used in scientific‐skeptical or hedging statements—words like “However,” “not been scientifically proven,” “limited evidence,” “more research needed,” and “pseudoscientific.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions of longevity and examples of individuals alleged to have lived beyond typical life spans.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ำ
    -0.06
    (Z
    -0.06
    シェ
    -0.06
     publik
    -0.06
     Real
    -0.06
    -word
    -0.06
    instruction
    -0.06
    Ber
    -0.06
    XA
    -0.06
    Instruction
    -0.06
    POSITIVE LOGITS
    итов
    0.07
     образования
    0.07
    Дата
    0.06
    ddl
    0.06
     Ballard
    0.06
    -Identifier
    0.06
     البر
    0.06
    鉄
    0.06
     retirees
    0.06
     Restricted
    0.06
    Act Density 0.030%

    No Known Activations