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

    Neuronpedia

    INDEX
    Explanations

    ability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鹡
    -0.06
     mattresses
    -0.06
     enterprises
    -0.06
     polyline
    -0.06
     novelist
    -0.06
    .PRO
    -0.06
     대통
    -0.06
     contraception
    -0.06
     aden
    -0.06
     ListTile
    -0.06
    POSITIVE LOGITS
    /Game
    0.07
    _scheme
    0.07
     вой
    0.07
    操纵
    0.07
    "struct
    0.07
     Registers
    0.07
    荣誉
    0.06
    انتشار
    0.06
     integration
    0.06
    forced
    0.06
    Act Density 0.155%

    No Known Activations