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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially decimal, fractional, or percentage values—in scientific measurements and statistics.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ีต
    -0.08
    (tt
    -0.06
    .getBoolean
    -0.06
    ันย
    -0.06
    ]+\
    -0.06
     APC
    -0.06
     priority
    -0.06
     noci
    -0.06
     Pont
    -0.06
     QPainter
    -0.06
    POSITIVE LOGITS
    (simp
    0.07
     معرف
    0.07
    ْح
    0.06
    SSFWorkbook
    0.06
    Workspace
    0.06
    ну
    0.06
    .Headers
    0.06
    更
    0.06
     vibrating
    0.06
    0.06
    Act Density 0.315%

    No Known Activations