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

    Neuronpedia

    INDEX
    Explanations

    names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    1.09
    </b>
    0.73
     it
    0.69
    ReadToEnd
    0.68
    AR
    0.66
     FISA
    0.65
    ON
    0.65
     Tully
    0.64
     (
    0.63
    os
    0.62
    POSITIVE LOGITS
    л
    1.13
    ل
    0.98
    ن
    0.94
    the
    0.90
    су
    0.89
    ນ
    0.86
    ہ
    0.85
    ра
    0.84
    ید
    0.83
    ت
    0.82
    Act Density 0.048%

    No Known Activations