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

    Neuronpedia

    INDEX
    Explanations

    lazily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.52
    ów
    1.20
    ě
    1.05
    ಮ
    1.03
    ید
    1.02
    es
    1.00
    ın
    0.99
    m
    0.97
    ի
    0.96
    p
    0.94
    POSITIVE LOGITS
     $
    1.02
     (
    0.93
     Partai
    0.90
    ายเป็น
    0.85
    StringBuilder
    0.84
     TestCase
    0.84
    arat
    0.84
     Asoci
    0.83
    IGroup
    0.83
    щика
    0.83
    Act Density 0.000%

    No Known Activations