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

    Neuronpedia

    INDEX
    Explanations

    Saskatchewan and Regina location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.96
    a
    0.91
    ä
    0.91
     i
    0.89
    ON
    0.82
     was
    0.81
     for
    0.80
     is
    0.78
    AP
    0.78
    St
    0.77
    POSITIVE LOGITS
    س
    1.18
    ن
    1.08
    स
    0.97
    સ
    0.93
    স
    0.90
    с
    0.89
    য়
    0.87
    িন
    0.87
    ন
    0.87
    ни
    0.86
    Act Density 0.001%

    No Known Activations