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

    Neuronpedia

    INDEX
    Explanations

    3d and arithmetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     क्षेत्र
    0.47
     teknoloj
    0.46
     perkembangan
    0.46
     orientado
    0.45
     posibilidad
    0.44
     persiapan
    0.44
     propo
    0.43
     prüfe
    0.42
    ڑک
    0.42
     intruders
    0.42
    POSITIVE LOGITS
    basename
    0.46
    proguard
    0.46
    愕
    0.45
    ShoppingCart
    0.43
    fillStyle
    0.42
    scriptions
    0.42
     incompre
    0.42
    警告
    0.42
    所述
    0.41
    umsuz
    0.41
    Act Density 0.044%

    No Known Activations