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

    Neuronpedia

    INDEX
    Explanations

    direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    敖
    -0.07
     tom
    -0.07
    nio
    -0.07
     השלישי
    -0.07
     некотор
    -0.07
     ill
    -0.06
     Carnegie
    -0.06
    .i
    -0.06
    [*
    -0.06
    leans
    -0.06
    POSITIVE LOGITS
     деле
    0.07
    方向
    0.07
    Genre
    0.07
     customizable
    0.07
     elek
    0.07
    خدام
    0.07
    Deque
    0.07
    Does
    0.07
    뭡
    0.07
    يرا
    0.07
    Act Density 0.019%

    No Known Activations