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

    Neuronpedia

    INDEX
    Explanations

    letterhead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ACIONES
    0.88
    ﮏ
    0.84
    ﺔ
    0.83
     ged
    0.82
    ים
    0.80
    ATIONS
    0.76
    ATED
    0.75
    ेशंस
    0.73
    ITIVE
    0.73
    ાઓ
    0.72
    POSITIVE LOGITS
    book
    1.45
    frame
    1.39
    storm
    1.39
    board
    1.39
    work
    1.36
    case
    1.34
    head
    1.34
    wear
    1.34
    bank
    1.34
    form
    1.33
    Act Density 0.900%

    No Known Activations