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

    Neuronpedia

    INDEX
    Explanations

    Instructions and permissions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Raise
    -0.07
     cattle
    -0.06
     raised
    -0.06
    کان
    -0.06
     Raw
    -0.06
    ới
    -0.06
    ícul
    -0.06
     }));↵
    -0.06
    _ARCH
    -0.06
    문제
    -0.06
    POSITIVE LOGITS
     sadness
    0.08
    ैं.
    0.07
     rating
    0.07
    ości
    0.07
    лик
    0.07
    aigned
    0.07
    ندية
    0.07
     الحي
    0.07
    /star
    0.06
    stitial
    0.06
    Act Density 0.196%

    No Known Activations