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

    Neuronpedia

    INDEX
    Explanations

    car

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.08
     broaden
    -0.08
    蒙
    -0.08
    咐
    -0.08
     adopted
    -0.07
     with
    -0.07
    口语
    -0.07
     Zinc
    -0.07
    Scott
    -0.07
    WG
    -0.07
    POSITIVE LOGITS
     car
    0.09
    iscrimination
    0.08
    نتائ
    0.08
     Cars
    0.08
    _fre
    0.08
    になる
    0.07
     העובדה
    0.07
    .requestFocus
    0.07
    アプリ
    0.07
    $arr
    0.07
    Act Density 0.054%

    No Known Activations