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

    Neuronpedia

    INDEX
    Explanations

    colored fur, hotel, game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ได้รับ
    0.46
    тов
    0.45
     Künstler
    0.42
     sauna
    0.41
    യിരുന്നു
    0.41
     põh
    0.41
     gikk
    0.41
     parecía
    0.40
     músico
    0.40
     साजिश
    0.40
    POSITIVE LOGITS
     abs
    0.54
    s
    0.50
    opol
    0.48
     aces
    0.46
    드
    0.46
    ﺢ
    0.46
    aturi
    0.46
    స
    0.45
     бү
    0.44
     ο
    0.44
    Act Density 0.000%

    No Known Activations