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

    Neuronpedia

    INDEX
    Explanations

    large quantities and scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    1.29
    ون
    1.27
    i
    1.19
    ના
    1.02
    س
    1.02
    dex
    0.98
    ס
    0.97
    ი
    0.96
    ي
    0.95
     it
    0.94
    POSITIVE LOGITS
    (
    1.02
    AM
    0.93
    th
    0.82
    리의
    0.80
    UT
    0.79
    ANG
    0.79
    த்தர
    0.77
    ahan
    0.76
     Byrd
    0.76
     Daher
    0.76
    Act Density 0.010%

    No Known Activations