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

    Neuronpedia

    INDEX
    Explanations

    times and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GFP
    0.99
    uerpo
    0.97
     Shash
    0.91
    uffled
    0.91
    apal
    0.89
    iedo
    0.88
    inggi
    0.88
    gev
    0.87
    کریاں
    0.86
    】，
    0.85
    POSITIVE LOGITS
     lä
    0.88
     just
    0.87
     št
    0.86
     čo
    0.84
     apparently
    0.84
     improb
    0.83
     perhaps
    0.82
     unsure
    0.81
     сус
    0.79
     zahr
    0.78
    Act Density 0.004%

    No Known Activations