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

    Neuronpedia

    INDEX
    Explanations

    math expressions and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अतिथि
    0.43
    制造商
    0.43
    ებული
    0.41
    餐厅
    0.41
    鳇
    0.41
     ذہنی
    0.40
     Girl
    0.40
     कम्पनी
    0.40
    িনবার্গ
    0.39
    蛋糕
    0.39
    POSITIVE LOGITS
    .-
    0.44
     multist
    0.40
    urid
    0.39
    ln
    0.39
     -
    0.39
     –
    0.38
    J
    0.38
     $-\
    0.38
    ,-
    0.37
     $-
    0.37
    Act Density 0.000%

    No Known Activations