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

    Neuronpedia

    INDEX
    Explanations

    data, date, country, adding, resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ivasena
    0.87
    ತಕ್ಕ
    0.86
     pâte
    0.85
    KURZBESCHREIBUNG
    0.84
     boar
    0.84
     ప్రశ్
    0.82
    కులు
    0.81
     gradioApp
    0.81
     nChar
    0.81
     Конечно
    0.80
    POSITIVE LOGITS
    个
    0.71
    み
    0.70
    প
    0.70
    iz
    0.66
    为
    0.66
    قال
    0.64
    ال
    0.63
    ed
    0.63
     Resources
    0.62
    З
    0.62
    Act Density 0.003%

    No Known Activations