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

    Neuronpedia

    INDEX
    Explanations

    Model & vehicle types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кмекер
    0.45
     kammam
    0.43
     velas
    0.42
    ोनेशिया
    0.42
    érir
    0.41
     patitth
    0.40
     PLANTS
    0.38
    .(*
    0.38
     pâle
    0.38
     paneles
    0.38
    POSITIVE LOGITS
    یده
    0.46
    ApiClient
    0.44
    ustin
    0.41
    '
    0.40
    ّ
    0.40
     Shap
    0.40
     skins
    0.39
     Lyle
    0.39
    ळा
    0.39
    ر
    0.39
    Act Density 0.057%

    No Known Activations