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

    Neuronpedia

    INDEX
    Explanations

    asking or speaking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     其
    0.57
    oulder
    0.48
    anken
    0.45
    其
    0.43
     त्यांची
    0.42
     ಅದರ
    0.41
     వారి
    0.40
    avier
    0.40
    有所
    0.40
    ่
    0.40
    POSITIVE LOGITS
     gratis
    0.51
    Де
    0.48
    Projekt
    0.44
     radon
    0.44
     topik
    0.44
     gratuito
    0.44
     cinq
    0.43
    Сегодня
    0.43
     zond
    0.43
     konser
    0.43
    Act Density 0.007%

    No Known Activations