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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anon
    -0.08
    895
    -0.07
    ajes
    -0.07
    ávání
    -0.06
    ilor
    -0.06
    -х
    -0.06
    (hw
    -0.06
    Seg
    -0.06
    )-(
    -0.06
     MediaTek
    -0.06
    POSITIVE LOGITS
    �
    0.07
     oath
    0.07
    province
    0.07
    -background
    0.06
     acı
    0.06
     Học
    0.06
    在线视频
    0.06
    UIViewController
    0.06
    Background
    0.06
    .getStyle
    0.06
    Act Density 0.004%

    No Known Activations