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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    秉
    -0.07
    祖
    -0.06
    .strftime
    -0.06
    条例
    -0.06
    זרח
    -0.06
    蹿
    -0.06
     рожд
    -0.06
     אצלנו
    -0.06
    _gradients
    -0.06
    POSITIVE LOGITS
    ⇔
    0.08
    ем
    0.07
     ;↵
    0.07
    โชค
    0.07
    〉
    0.07
    )|
    0.07
    �
    0.06
    共
    0.06
     Campo
    0.06
    ٬
    0.06
    Act Density 0.009%

    No Known Activations