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

    Neuronpedia

    INDEX
    Explanations

    specialized domain terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    试图
    0.45
    రుగు
    0.44
    减肥
    0.44
     nia
    0.43
     După
    0.41
    HttpRequest
    0.40
    гія
    0.40
     hår
    0.40
     thérapeut
    0.39
     idé
    0.39
    POSITIVE LOGITS
    bar
    0.43
    ಸ್ಸ
    0.41
    own
    0.40
    be
    0.39
     Cem
    0.38
    ب
    0.38
    cast
    0.38
    Mult
    0.38
    Montana
    0.38
    elos
    0.38
    Act Density 0.000%

    No Known Activations