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

    Neuronpedia

    INDEX
    Explanations

    AND geographic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    se
    0.91
    б
    0.80
    ich
    0.79
    és
    0.77
    π
    0.77
    ge
    0.77
    pa
    0.76
    uch
    0.74
    naire
    0.74
    ε
    0.73
    POSITIVE LOGITS
     अभिगमन
    0.99
     berfungsi
    0.95
    ыл
    0.90
     duyệt
    0.90
     время
    0.89
    ಹಾಸ
    0.89
     답
    0.87
     Forests
    0.87
     ଗ
    0.87
     açıkl
    0.86
    Act Density 0.000%

    No Known Activations