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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     function
    -0.07
     afin
    -0.06
    Various
    -0.06
    며
    -0.06
     Def
    -0.06
    _Params
    -0.06
     Ave
    -0.06
    .od
    -0.06
     Ten
    -0.06
    _PIPELINE
    -0.06
    POSITIVE LOGITS
     MICRO
    0.07
    وري
    0.07
    usto
    0.07
    punk
    0.07
    蛾
    0.07
     bott
    0.07
     enactment
    0.06
    äch
    0.06
    パー
    0.06
    מוז
    0.06
    Act Density 0.158%

    No Known Activations