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

    Neuronpedia

    INDEX
    Explanations

    ests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ્સ
    1.14
    to
    1.03
    ski
    1.01
    the
    1.00
    ﺴ
    0.99
    ts
    0.98
    t
    0.92
    tz
    0.87
    tion
    0.86
    ט
    0.86
    POSITIVE LOGITS
    ourcing
    1.53
    ourced
    1.48
    pectral
    1.48
    chool
    1.46
    pecial
    1.45
    htein
    1.42
    ponsor
    1.41
    ources
    1.41
    ufficient
    1.37
    ensitivity
    1.36
    Act Density 0.733%

    No Known Activations