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

    Neuronpedia

    INDEX
    Explanations

    table headers and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ――
    0.92
    "--
    0.84
    －－
    0.83
    ＰＥ
    0.75
    ――――
    0.75
    oise
    0.75
     বাহির
    0.74
    expires
    0.74
     inspired
    0.74
     expiry
    0.73
    POSITIVE LOGITS
    异常
    0.81
    エラー
    0.80
     Error
    0.76
    Carpenter
    0.75
    ucidation
    0.75
    Ошибка
    0.74
    応答
    0.73
    皞
    0.73
    ውነተኛ
    0.72
     Список
    0.71
    Act Density 0.057%

    No Known Activations