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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     		↵
    -0.08
    دفع
    -0.07
     חג
    -0.07
    接管
    -0.07
    ===========↵
    -0.07
    ธนา
    -0.07
     אל
    -0.07
    ({_
    -0.07
    (lua
    -0.07
     tussen
    -0.07
    POSITIVE LOGITS
    _rev
    0.08
    history
    0.06
     phê
    0.06
    写的
    0.06
    WAIT
    0.06
    𬤇
    0.06
    _COND
    0.06
    .RequestParam
    0.06
    Rate
    0.06
     happy
    0.06
    Act Density 0.001%

    No Known Activations