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

    Neuronpedia

    INDEX
    Explanations

    gross

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เภ
    -0.07
    녜
    -0.07
    ㋯
    -0.07
    lift
    -0.07
    냔
    -0.07
    raud
    -0.07
     Isn
    -0.07
    Ņ
    -0.07
    舍
    -0.07
    Главная
    -0.07
    POSITIVE LOGITS
    一人
    0.07
    _markup
    0.07
     include
    0.07
    𥔲
    0.06
    ﰢ
    0.06
    مجلس
    0.06
     salt
    0.06
    uring
    0.06
    ירים
    0.06
    盖
    0.06
    Act Density 0.003%

    No Known Activations