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

    Neuronpedia

    INDEX
    Explanations

    be swift

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یده
    0.55
    ﻋ
    0.43
    ﻓ
    0.42
    ﻥ
    0.42
    ﻣ
    0.42
    вається
    0.42
     threefold
    0.40
     a
    0.40
     methodical
    0.38
    дите
    0.38
    POSITIVE LOGITS
    ン
    0.67
    ة
    0.67
    us
    0.66
     of
    0.63
     của
    0.62
    ü
    0.60
    é
    0.59
    of
    0.57
    ă
    0.56
     několika
    0.55
    Act Density 0.000%

    No Known Activations