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

    Neuronpedia

    INDEX
    Explanations

    giving out or distributing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    -1.92
    ↵
    -1.90
     \
    -1.84
    s
    -1.82
     “
    -1.76
     About
    -1.72
    }$
    -1.71
    V
    -1.70
     pinnacle
    -1.65
     .
    -1.64
    POSITIVE LOGITS
    疍
    2.20
     壁纸
    2.05
    愴
    1.94
     ヌード
    1.89
    谖
    1.86
    锱
    1.82
    katalog
    1.79
    鰊
    1.77
    鳢
    1.75
    彣
    1.73
    Act Density 0.014%

    No Known Activations