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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron fires on quantitative expressions—numbers, counts, measures, and other statistical/numeric tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -set
    -0.06
    .Constraint
    -0.06
    country
    -0.06
    acked
    -0.06
     mac
    -0.06
    _CHANNEL
    -0.06
    .navigation
    -0.06
    .adj
    -0.06
    .Marshal
    -0.06
     Belize
    -0.06
    POSITIVE LOGITS
    ajax
    0.07
     قبل
    0.07
     písem
    0.07
    /${
    0.06
     Supplementary
    0.06
     Pag
    0.06
    azaar
    0.06
     AX
    0.06
    лений
    0.06
    grades
    0.06
    Act Density 0.038%

    No Known Activations