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

    Neuronpedia

    INDEX
    Explanations

    system package management commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bungen
    0.62
    Commission
    0.61
    椿
    0.60
     Commission
    0.60
    принима
    0.58
     LMB
    0.58
     commission
    0.58
    𝐑
    0.57
    𝙍
    0.57
     Mare
    0.57
    POSITIVE LOGITS
     tele
    0.66
    tele
    0.64
     مدير
    0.61
    ald
    0.59
    adet
    0.57
     telemetry
    0.57
     Tele
    0.57
     telle
    0.56
     દા
    0.56
    Tele
    0.55
    Act Density 0.179%

    No Known Activations