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

    Neuronpedia

    INDEX
    Explanations

    description:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beheld
    0.41
     irradiation
    0.40
     했다
    0.39
     था
    0.38
     rhy
    0.38
     яким
    0.38
    ។
    0.38
     сви
    0.38
     Бүген
    0.37
     TextStyle
    0.37
    POSITIVE LOGITS
    at
    0.58
    സ
    0.44
    is
    0.43
    ס
    0.43
    ق
    0.43
    atched
    0.43
    ió
    0.42
    el
    0.40
    as
    0.40
    io
    0.40
    Act Density 0.013%

    No Known Activations