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

    Neuronpedia

    INDEX
    Explanations

    articles and prepositions

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens (especially decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Yog
    -0.08
    epsilon
    -0.08
    hc
    -0.07
    Marshal
    -0.07
    來
    -0.06
     parasites
    -0.06
     utc
    -0.06
     来
    -0.06
    wor
    -0.06
     wig
    -0.06
    POSITIVE LOGITS
    .Classes
    0.07
     spol
    0.07
     thriller
    0.07
     effortless
    0.06
     HF
    0.06
     adequately
    0.06
    FRINGEMENT
    0.06
    ENOMEM
    0.06
     ASC
    0.06
     UTIL
    0.06
    Act Density 0.053%

    No Known Activations