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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .paginator
    -0.07
     cerv
    -0.07
     قد
    -0.07
    Think
    -0.07
     toward
    -0.06
    当场
    -0.06
    .Aggressive
    -0.06
    /light
    -0.06
     tends
    -0.06
    _public
    -0.06
    POSITIVE LOGITS
    诀
    0.07
    国外
    0.07
    و
    0.07
    סר
    0.07
     datatype
    0.07
    ව
    0.07
    ירת
    0.07
    dek
    0.06
    ,C
    0.06
    学员
    0.06
    Act Density 0.001%

    No Known Activations