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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    /q
    -0.07
     Kar
    -0.07
    (USER
    -0.07
     Peterson
    -0.07
    嫌弃
    -0.07
    نق
    -0.07
    uy
    -0.07
    Crear
    -0.06
    .Normalize
    -0.06
    [c
    -0.06
    POSITIVE LOGITS
    _voltage
    0.07
    )||(
    0.07
    亿万
    0.07
    盷
    0.07
     weapons
    0.07
    ...↵↵↵↵
    0.07
    מרים
    0.07
    windows
    0.07
    iversal
    0.07
    blink
    0.06
    Act Density 0.001%

    No Known Activations