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

    Neuronpedia

    INDEX
    Explanations

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hón
    0.75
    a
    0.74
    ictwo
    0.72
    sempel
    0.72
    e
    0.71
    depends
    0.70
     μία
    0.69
    होम
    0.69
     महिन
    0.69
    puede
    0.69
    POSITIVE LOGITS
    ಗಳ
    0.81
     Res
    0.75
     inner
    0.74
     tidal
    0.74
     fragrant
    0.74
     dusty
    0.74
     curbing
    0.72
     authentic
    0.72
     Commun
    0.72
    .,
    0.71
    Act Density 0.428%

    No Known Activations