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

    Neuronpedia

    INDEX
    Explanations

    "i'll" or "i've" initiations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nél
    1.00
    on
    0.97
    вати
    0.88
    n
    0.87
    리
    0.86
    ной
    0.80
    nements
    0.75
    지
    0.73
    тов
    0.72
    ली
    0.71
    POSITIVE LOGITS
    I
    1.00
    0
    0.98
    ال
    0.85
    ERS
    0.79
    1
    0.78
    ı
    0.71
    েন
    0.70
    Data
    0.68
    IER
    0.67
    Educ
    0.66
    Act Density 0.514%

    No Known Activations