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

    Neuronpedia

    INDEX
    Explanations

    bodily functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    서
    3.36
    ية
    3.06
    り
    3.03
    いた
    2.72
    ний
    2.67
    ح
    2.63
    сть
    2.59
    theless
    2.56
    ductory
    2.55
    ছেন
    2.52
    POSITIVE LOGITS
    i
    3.20
    lardan
    2.89
    ierten
    2.77
    e
    2.73
    t
    2.67
    iu
    2.66
    mö
    2.58
    eed
    2.56
    ições
    2.55
    ỡng
    2.55
    Act Density 1.722%

    No Known Activations