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

    Neuronpedia

    INDEX
    Explanations

    submit or submission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    о
    1.12
    я
    1.00
    е
    0.98
    а
    0.96
    ρα
    0.95
    у
    0.95
    ۲
    0.89
    и
    0.89
    لی
    0.85
    یشه
    0.81
    POSITIVE LOGITS
    at
    1.29
    as
    1.25
    T
    1.14
    i
    1.09
     submission
    1.02
     submissions
    0.98
     submit
    0.98
    Submit
    0.92
    ت
    0.92
     submitted
    0.91
    Act Density 0.023%

    No Known Activations