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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IE
    -0.07
    　　　　 　
    -0.06
    _mirror
    -0.06
     tabla
    -0.06
    Detalle
    -0.06
    (pro
    -0.06
    Пос
    -0.06
    \uB
    -0.06
    参照
    -0.06
    .Regular
    -0.06
    POSITIVE LOGITS
     граждан
    0.07
    ellites
    0.07
     공동
    0.07
    '=
    0.07
    啪
    0.07
    ilinear
    0.07
     slam
    0.07
     aute
    0.07
     Bers
    0.07
     دن
    0.06
    Act Density 0.025%

    No Known Activations