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

    Neuronpedia

    INDEX
    Explanations

    requirements and needs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sep
    -0.07
    _aug
    -0.06
    ‫
    -0.06
    _JS
    -0.06
    venta
    -0.06
    toLocale
    -0.06
     ‫
    -0.06
    roles
    -0.06
     kulak
    -0.06
     bureau
    -0.06
    POSITIVE LOGITS
     Serv
    0.07
    enity
    0.07
     Angelo
    0.06
    범
    0.06
    omatic
    0.06
     часто
    0.06
     слово
    0.06
    riangle
    0.06
    湿
    0.06
    ادي
    0.06
    Act Density 0.054%

    No Known Activations