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

    Neuronpedia

    INDEX
    Explanations

    initial state particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    preloader
    -0.82
    Ŵ
    -0.77
    wiec
    -0.75
     Peña
    -0.75
    werken
    -0.75
    lidos
    -0.75
    ATTACK
    -0.74
    工程
    -0.73
    電車
    -0.72
    camos
    -0.72
    POSITIVE LOGITS
     getString
    0.80
     оско
    0.80
     hard
    0.78
     stiff
    0.77
    カンド
    0.74
     жест
    0.73
     Lars
    0.72
     biais
    0.71
     jú
    0.70
     guilty
    0.67
    Act Density 0.017%

    No Known Activations