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

    Neuronpedia

    INDEX
    Explanations

    capturing emotion and celebrating self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ст
    0.54
    лет
    0.50
     объ
    0.48
    чек
    0.47
     ежедневно
    0.47
    𝜁
    0.47
    visually
    0.46
    лся
    0.46
     stargazerCount
    0.46
    ırs
    0.45
    POSITIVE LOGITS
    方的
    0.46
     T
    0.45
     R
    0.44
    口感
    0.44
    పా
    0.43
     H
    0.43
    πα
    0.43
     lam
    0.43
    不过
    0.42
     Daw
    0.41
    Act Density 0.002%

    No Known Activations