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

    Neuronpedia

    INDEX
    Explanations

    probability measures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.08
    %;
    -0.07
    �
    -0.07
    Ĩ
    -0.06
    🔰
    -0.06
    💠
    -0.06
    '.
    -0.06
    BI
    -0.06
    BAD
    -0.06
     monitor
    -0.06
    POSITIVE LOGITS
    .friend
    0.07
    (today
    0.07
    זכה
    0.07
    西医
    0.07
    쌌
    0.07
    皇后
    0.07
    "]);
↵
    0.07
     Floors
    0.07
    income
    0.07
    ファッション
    0.06
    Act Density 0.009%

    No Known Activations