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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ylinder
    -0.07
    .commands
    -0.06
    god
    -0.06
    чила
    -0.06
     Surprise
    -0.06
     Unc
    -0.06
    și
    -0.06
     willen
    -0.06
    alc
    -0.06
    ामग
    -0.06
    POSITIVE LOGITS
    _nama
    0.07
    .getWindow
    0.07
    (album
    0.07
    .chart
    0.06
     Flem
    0.06
     конт
    0.06
    حب
    0.06
     Xã
    0.06
     ');↵
    0.06
    ."""↵↵
    0.06
    Act Density 0.017%

    No Known Activations