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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    摄像
    -0.07
    ⨀
    -0.07
     impe
    -0.06
    商报
    -0.06
    좉
    -0.06
    这件事情
    -0.06
     does
    -0.06
    瑜
    -0.06
    �
    -0.06
     Deutsche
    -0.06
    POSITIVE LOGITS
     الأساس
    0.08
    mach
    0.08
     конструк
    0.08
     validationResult
    0.07
    checks
    0.07
     Sang
    0.07
    lon
    0.07
     discs
    0.07
    -point
    0.07
    (selector
    0.07
    Act Density 0.028%

    No Known Activations