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

    Neuronpedia

    INDEX
    Explanations

    duplication or repetition

    np_max-act · gemini-2.0-flash

    questions related to software installation and configuration issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on numeric quantifiers and related words indicating counts or ordinals (e.g., “two,” “another,” “second”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Joint
    -0.08
     unlike
    -0.07
     S
    -0.07
     joints
    -0.07
     stiffness
    -0.06
     Monsters
    -0.06
    ювання
    -0.06
    students
    -0.06
    sig
    -0.06
     pint
    -0.06
    POSITIVE LOGITS
    าษฎ
    0.07
    OKIE
    0.06
    Inform
    0.06
     Kurul
    0.06
    tml
    0.06
    tplib
    0.06
    optim
    0.06
    clone
    0.06
    ccoli
    0.06
     fw
    0.06
    Act Density 0.234%

    No Known Activations