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

    Neuronpedia

    INDEX
    Explanations

    challenges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    支援
    -0.07
    Recording
    -0.07
     double
    -0.06
     žid
    -0.06
     ча
    -0.06
    された
    -0.06
     apparel
    -0.06
    )initWithFrame
    -0.06
     نیم
    -0.06
    .listeners
    -0.06
    POSITIVE LOGITS
    md
    0.07
    тар
    0.06
    ....↵↵
    0.06
    (us
    0.06
    usahaan
    0.06
     Priv
    0.06
    ....
    0.06
    уй
    0.06
     trolling
    0.06
    _ALARM
    0.06
    Act Density 0.077%

    No Known Activations