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

    Neuronpedia

    INDEX
    Explanations

    increment count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     соответствующие
    0.52
     लीजिएगा
    0.46
    нологи
    0.46
    archiw
    0.46
    之間
    0.45
    🎹
    0.45
     також
    0.45
    olutely
    0.45
    坪
    0.44
    😨
    0.44
    POSITIVE LOGITS
     increased
    0.86
     increases
    0.84
     increment
    0.83
     increase
    0.79
     increments
    0.77
     increasing
    0.67
     увеличи
    0.67
     aumenta
    0.66
     incremento
    0.64
     Increases
    0.62
    Act Density 0.037%

    No Known Activations