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

    Neuronpedia

    INDEX
    Explanations

    import statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र्यंत
    0.56
    Ό
    0.47
    ༔
    0.46
     ভাতা
    0.44
     인한
    0.44
    .},
    0.43
     मसल्स
    0.43
    ³,
    0.43
    НЫ
    0.43
     هذا
    0.43
    POSITIVE LOGITS
     uye
    0.46
     pubblico
    0.45
    ↵↵
    0.45
     hanno
    0.42
     uomini
    0.42
     anche
    0.42
     nuova
    0.42
     police
    0.41
     personaggio
    0.41
     dispatch
    0.41
    Act Density 0.011%

    No Known Activations