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

    Neuronpedia

    INDEX
    Explanations

    italic text formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &/
    1.20
     ឬ
    1.13
     või
    1.12
    によっては
    1.08
     yoki
    1.07
    或是
    1.06
     Möglich
    1.03
     किंवा
    1.03
     estranged
    1.02
    ahanglan
    0.99
    POSITIVE LOGITS
    .
    0.78
     The
    0.68
     بعنوان
    0.67
    The
    0.66
     кукуру
    0.64
     symbolized
    0.62
     at
    0.62
    0.61
     ()
    0.61
    :
    0.59
    Act Density 2.214%

    No Known Activations