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

    Neuronpedia

    INDEX
    Explanations

    double blind trials or omelet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ני
    0.73
    ि
    0.70
    ﻨ
    0.70
     І
    0.70
    ﻬ
    0.69
     MODKEY
    0.67
     configurações
    0.63
    п
    0.63
    І
    0.63
     }}$,
    0.62
    POSITIVE LOGITS
    ت
    0.83
    or
    0.73
    (
    0.72
    at
    0.71
    as
    0.70
    to
    0.70
    us
    0.66
    et
    0.64
    un
    0.63
    ed
    0.63
    Act Density 0.007%

    No Known Activations