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

    Neuronpedia

    INDEX
    Explanations

    image file names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ac
    1.10
    -
    0.95
    un
    0.86
    ۰
    0.82
    EE
    0.80
    Z
    0.80
    IC
    0.79
    W
    0.79
    Q
    0.79
    dec
    0.78
    POSITIVE LOGITS
    jpg
    0.95
    将
    0.85
    ನಲ್ಲಿ
    0.75
    饪
    0.75
    有一些
    0.74
     theologian
    0.74
     placée
    0.74
     resa
    0.72
    𝙞
    0.71
     trono
    0.71
    Act Density 0.001%

    No Known Activations