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

    Neuronpedia

    INDEX
    Explanations

    isk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Interval
    -0.07
     جي
    -0.07
    stanbul
    -0.06
    Positions
    -0.06
     Cic
    -0.06
     undermine
    -0.06
    sequ
    -0.06
     Ґ
    -0.06
    [ind
    -0.06
    lation
    -0.06
    POSITIVE LOGITS
    Respond
    0.07
    _RESET
    0.07
     contribute
    0.06
     writeln
    0.06
     newRow
    0.06
     Frost
    0.06
     unexpected
    0.06
    маг
    0.06
     Spoj
    0.06
     attend
    0.06
    Act Density 0.015%

    No Known Activations