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

    Neuronpedia

    INDEX
    Explanations

    list, react, youtube, data, sort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reb
    0.76
    net
    0.75
     episode
    0.68
    ond
    0.67
     colds
    0.66
    grado
    0.66
    что
    0.65
     opp
    0.65
    vid
    0.65
     voj
    0.65
    POSITIVE LOGITS
    ወቅ
    1.01
    ీల
    1.00
     मिळाल
    0.99
     የወ
    0.95
    ूहिक
    0.94
    ows
    0.93
     pioneered
    0.93
    ätzung
    0.92
    yw
    0.92
     رئيس
    0.92
    Act Density 0.000%

    No Known Activations