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

    Neuronpedia

    INDEX
    Explanations

    say "a"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olded
    0.69
    ihad
    0.67
    Magnitude
    0.67
    hadas
    0.65
    ூட
    0.63
    ereal
    0.63
    okay
    0.61
    just
    0.61
     கலந்து
    0.61
    狰
    0.61
    POSITIVE LOGITS
     excellently
    0.77
     nicely
    0.69
     என்ப
    0.68
    氶
    0.68
    umac
    0.66
     solchen
    0.64
     නිසා
    0.64
     Güzel
    0.63
     זאת
    0.61
     parfaitement
    0.61
    Act Density 0.075%

    No Known Activations