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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    анта
    -0.07
    TAIL
    -0.07
    ‌پدی
    -0.07
    /*
↵
    -0.07
     ヽ
    -0.06
    conexao
    -0.06
    (),↵↵
    -0.06
     col
    -0.06
    іту
    -0.06
     Newfoundland
    -0.06
    POSITIVE LOGITS
     Wenger
    0.06
     نسبة
    0.06
    105
    0.06
    SEP
    0.06
    (setting
    0.06
    西
    0.06
    有点
    0.06
     �
    0.06
     clicked
    0.06
     reassuring
    0.06
    Act Density 0.000%

    No Known Activations