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

    Neuronpedia

    INDEX
    Explanations

    ¡Claro que sí!

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.59
    rige
    0.55
    นด์
    0.49
     Grove
    0.48
    erst
    0.48
    arne
    0.47
    Kö
    0.47
    HttpStatusCode
    0.47
    рко
    0.46
    O
    0.46
    POSITIVE LOGITS
     cellophane
    0.59
    ᱕
    0.58
    的主
    0.57
    nu
    0.57
     manicure
    0.57
     franchises
    0.57
     debat
    0.57
    ))(
    0.56
    ‌
    0.55
     veranda
    0.55
    Act Density 0.001%

    No Known Activations