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

    Neuronpedia

    INDEX
    Explanations

    in phrases like "in office"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    0.65
    ت
    0.61
    ት
    0.59
    t
    0.57
    v
    0.56
    т
    0.55
    n
    0.54
    ка
    0.53
    ك
    0.53
    н
    0.52
    POSITIVE LOGITS
     ketone
    0.53
     pegs
    0.48
     triage
    0.48
     KPSS
    0.48
     telescope
    0.48
     থান
    0.46
     semiconductor
    0.45
     glycogen
    0.45
     spasms
    0.45
     classification
    0.45
    Act Density 0.038%

    No Known Activations