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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lose
    -0.07
    有条件的
    -0.07
    毫无
    -0.07
     Açık
    -0.07
    沮
    -0.07
    бав
    -0.07
    Stroke
    -0.07
    �
    -0.07
    琨
    -0.07
     boosted
    -0.07
    POSITIVE LOGITS
     кров
    0.07
    ieg
    0.07
    变速箱
    0.07
     Bangladesh
    0.07
     conn
    0.07
    唱片
    0.07
     chr
    0.07
    =b
    0.07
    ⟫
    0.07
     drama
    0.06
    Act Density 0.015%

    No Known Activations