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

    Neuronpedia

    INDEX
    Explanations

    culture in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Elapsed
    2.94
    क्षिप्त
    2.52
     ulcer
    2.49
     peduncul
    2.47
    amese
    2.41
    рано
    2.35
     Assume
    2.31
    貌
    2.29
    ät
    2.27
     unary
    2.27
    POSITIVE LOGITS
    RECTION
    2.41
    𝒐
    2.31
     المللی
    2.30
    ا
    2.27
    ாக
    2.23
    وڑ
    2.21
    riculum
    2.20
    ה
    2.20
    ᥒ
    2.17
    newBuilder
    2.14
    Act Density 0.994%

    No Known Activations