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

    Neuronpedia

    INDEX
    Explanations

    professor, describe, horse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tics
    1.23
    ларды
    1.02
    торое
    0.94
    ip
    0.90
    nosed
    0.88
    ிறது
    0.86
    yb
    0.86
    ыр
    0.84
    torrent
    0.84
    ты
    0.84
    POSITIVE LOGITS
    ش
    1.05
    ف
    0.99
    ین
    0.94
    рд
    0.93
     artiste
    0.93
     étage
    0.93
    лага
    0.92
     occupé
    0.91
    Я
    0.90
    奻
    0.90
    Act Density 0.000%

    No Known Activations