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

    Neuronpedia

    INDEX
    Explanations

    checking for updates or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಇದ
    0.45
    ayya
    0.45
    interesse
    0.44
     Ips
    0.44
    iras
    0.43
    क्रोश
    0.43
    去
    0.43
    ering
    0.42
    arga
    0.42
     Defender
    0.42
    POSITIVE LOGITS
    тельной
    0.55
    כּ
    0.46
    0.45
     Сі
    0.44
    tte
    0.44
     أو
    0.43
    ॉयड
    0.43
    ن
    0.43
    ڤ
    0.43
    تك
    0.43
    Act Density 0.002%

    No Known Activations