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

    Neuronpedia

    INDEX
    Explanations

    beaver, dams, pelts, Avalanche

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ش
    1.27
    지
    1.00
    ला
    0.99
    شون
    0.93
    ری
    0.93
    ج
    0.91
    적
    0.91
    al
    0.90
    ant
    0.89
     as
    0.86
    POSITIVE LOGITS
    '
    1.09
    -
    1.05
    (
    0.98
     Avalanche
    0.80
     jahr
    0.75
     Problems
    0.74
    [
    0.74
     Economics
    0.73
     Springs
    0.71
     fürs
    0.71
    Act Density 0.002%

    No Known Activations