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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    谢
    -0.07
    犰
    -0.07
    塑胶
    -0.07
    宣布
    -0.07
    힐
    -0.07
    reak
    -0.07
     Phill
    -0.07
    ,the
    -0.06
    서비스
    -0.06
    ');
↵
↵
    -0.06
    POSITIVE LOGITS
    𝑄
    0.08
     evacuated
    0.08
    _sessions
    0.08
     Lent
    0.07
    bred
    0.07
    spent
    0.07
     pertinent
    0.07
     argv
    0.07
    щин
    0.07
    GRAM
    0.07
    Act Density 0.011%

    No Known Activations