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

    Neuronpedia

    INDEX
    Explanations

    PARAMETER assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     спи
    0.80
     Пол
    0.78
     образу
    0.75
     જા
    0.75
     आइस
    0.75
     historique
    0.75
     ро
    0.74
     nelle
    0.73
    ्स
    0.73
    看了
    0.72
    POSITIVE LOGITS
    xas
    0.82
    xq
    0.81
    el
    0.77
     combatir
    0.76
    empuan
    0.76
    常量
    0.75
    fyp
    0.74
     ನ್ಯಾಯ
    0.74
     juego
    0.73
    imų
    0.73
    Act Density 0.004%

    No Known Activations