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

    Neuronpedia

    INDEX
    Explanations

    measurements and rules

    np_max-act · gemini-2.0-flash

    The neuron spots numeric measurements—particularly statistical numbers (counts, rates, percentages, etc.)—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    bubble
    -0.07
    avir
    -0.06
     Despite
    -0.06
     worth
    -0.06
    ayı
    -0.06
     These
    -0.06
    !!
    -0.06
     Bain
    -0.06
     [\
    -0.06
    략
    -0.06
    POSITIVE LOGITS
    NAME
    0.07
    andidates
    0.07
    _Enc
    0.07
    /(?
    0.07
    (INVOKE
    0.06
     holistic
    0.06
     허
    0.06
     вис
    0.06
    >()->
    0.06
     CURLOPT
    0.06
    Act Density 0.207%

    No Known Activations