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

    Neuronpedia

    INDEX
    Explanations

    working with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اتی
    0.76
     পড়ুন
    0.72
     vem
    0.72
    য়
    0.71
    ة
    0.71
     spraying
    0.68
    sant
    0.67
     coinc
    0.67
    ح
    0.67
    .__
    0.65
    POSITIVE LOGITS
    with
    0.78
     समक्ष
    0.75
    holds
    0.75
    ্স
    0.75
    getColumn
    0.74
     Toni
    0.74
    subTest
    0.73
    as
    0.72
    ्रल
    0.71
     odm
    0.71
    Act Density 0.011%

    No Known Activations