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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens, particularly decimal numbers (including negative and fractional numeric literals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _status
    -0.08
    /AP
    -0.07
    Clin
    -0.07
     matriz
    -0.07
     channels
    -0.07
     channel
    -0.06
    ificantly
    -0.06
     является
    -0.06
    ологія
    -0.06
     microbial
    -0.06
    POSITIVE LOGITS
    (-
    0.08
    ))+
    0.07
     (-
    0.07
     ib
    0.07
     Demp
    0.06
     {-
    0.06
    的手
    0.06
    237
    0.06
    ==-
    0.06
     seized
    0.06
    Act Density 0.007%

    No Known Activations