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

    Neuronpedia

    INDEX
    Explanations

    instructions/documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     קיש
    -0.07
     birka
    -0.07
    刪
    -0.07
    幪
    -0.07
    _CREATED
    -0.07
     מבוסס
    -0.07
     unnecessarily
    -0.07
     bodyParser
    -0.06
    �
    -0.06
    馁
    -0.06
    POSITIVE LOGITS
     folding
    0.07
    σ
    0.07
    查询
    0.07
    Usually
    0.07
     prom
    0.06
    mm
    0.06
     z
    0.06
    ように
    0.06
     pow
    0.06
    時候
    0.06
    Act Density 0.020%

    No Known Activations