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

    Neuronpedia

    INDEX
    Explanations

    foreign language fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *
    1.58
    >
    1.42
    (´
    1.38
     часы
    1.37
    NA
    1.35
    TH
    1.33
     первую
    1.33
     denominated
    1.33
    NO
    1.32
    NOV
    1.31
    POSITIVE LOGITS
    m
    1.87
    е
    1.73
    n
    1.69
    se
    1.67
    ness
    1.64
    ें
    1.59
    м
    1.57
    ك
    1.55
    ين
    1.53
    и
    1.41
    Act Density 0.102%

    No Known Activations