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

    Neuronpedia

    INDEX
    Explanations

    numbers and ISA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eğer
    0.45
     पर
    0.40
     zeker
    0.39
    หว
    0.39
     mutlaka
    0.39
    妇
    0.39
     большая
    0.38
    ద్య
    0.38
     druk
    0.38
     yeter
    0.38
    POSITIVE LOGITS
    olids
    0.49
     verwendet
    0.48
    upakan
    0.47
    .。
    0.46
     त्यांनी
    0.45
    accharides
    0.45
     verwenden
    0.45
    utzt
    0.44
    obuf
    0.44
    archiw
    0.44
    Act Density 0.003%

    No Known Activations