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

    Neuronpedia

    INDEX
    Explanations

    tables and code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    இந்திய
    0.46
     तेंदुलकर
    0.44
    kite
    0.44
    ഹ്ലാദ
    0.43
    ക്കാരി
    0.43
    kort
    0.41
    kei
    0.41
     einge
    0.40
    zewski
    0.39
    طيب
    0.39
    POSITIVE LOGITS
     жур
    0.44
    や
    0.43
     mutate
    0.42
     avons
    0.42
     συνε
    0.38
    ;
    0.38
    OF
    0.38
    的全
    0.38
    тере
    0.37
     純
    0.37
    Act Density 0.008%

    No Known Activations