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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron primarily detects numeric tokens (e.g. list item numbers, durations, quantities) in the text.

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

    content related to lesson structure and course organization in educational contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     HTMLElement
    -0.07
     matte
    -0.06
     Öğ
    -0.06
     breakpoint
    -0.06
    _Tool
    -0.06
     KV
    -0.06
     karşısında
    -0.06
    문
    -0.06
     SimpleName
    -0.06
     Sequ
    -0.06
    POSITIVE LOGITS
    Registered
    0.07
    �
    0.06
    relative
    0.06
    itness
    0.06
    Award
    0.06
     beaut
    0.06
    _integer
    0.06
     specifically
    0.06
    />\
    0.06
    Printing
    0.06
    Act Density 0.048%

    No Known Activations