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

    Neuronpedia

    INDEX
    Explanations

    corollaries, consequences, and particulars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কে
    0.82
    ERS
    0.69
    เรา
    0.65
    อย่างไร
    0.65
     sial
    0.65
    आई
    0.64
    ল
    0.64
     lote
    0.64
    ভাবে
    0.63
     subside
    0.63
    POSITIVE LOGITS
    on
    0.95
    a
    0.90
    c
    0.84
    ok
    0.79
    averaged
    0.78
    corollary
    0.77
    altering
    0.77
    onn
    0.75
    altered
    0.74
    aq
    0.72
    Act Density 0.001%

    No Known Activations