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

    Neuronpedia

    INDEX
    Explanations

    from time import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.71
    ها
    0.66
    ுகிற
    0.59
     on
    0.57
    ுகிறார்கள்
    0.56
    OR
    0.52
    ยนต์
    0.52
    RR
    0.52
    ،
    0.51
    टिंग
    0.50
    POSITIVE LOGITS
    t
    0.87
    ν
    0.76
    u
    0.75
    im
    0.74
    in
    0.73
    де
    0.71
    γ
    0.71
    import
    0.71
    σ
    0.71
    to
    0.69
    Act Density 4.529%

    No Known Activations