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

    Neuronpedia

    INDEX
    Explanations

    What's Wrong, What's Going, What's up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indeed
    0.83
    os
    0.79
    l
    0.77
    as
    0.73
     throughout
    0.72
     conform
    0.71
    to
    0.70
    ோர
    0.70
    ताई
    0.69
     forse
    0.68
    POSITIVE LOGITS
     been
    1.61
    been
    1.48
     Been
    1.35
     BEEN
    1.33
     gotta
    1.06
    Been
    1.02
     Gonna
    1.00
     været
    0.97
     gonna
    0.96
     sido
    0.93
    Act Density 0.002%

    No Known Activations