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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric values with decimal points—especially statistics reported in parentheses (e.g. proportions or p-values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ака
    -0.07
     rebounds
    -0.07
    &,
    -0.06
    MODULE
    -0.06
    =v
    -0.06
    ACT
    -0.06
     punching
    -0.06
    Europe
    -0.06
    MOD
    -0.06
     Maple
    -0.06
    POSITIVE LOGITS
    .telegram
    0.06
    .StatusCode
    0.06
    Crud
    0.06
    إ
    0.06
     نمود
    0.06
    ереж
    0.06
     فرهنگ
    0.06
    -FIRST
    0.06
    ＼↵
    0.06
    endencies
    0.06
    Act Density 0.007%

    No Known Activations