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

    Neuronpedia

    INDEX
    Explanations

    PHP error suppression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ere
    0.63
    pe
    0.62
    ot
    0.60
    il
    0.58
    erv
    0.58
    ol
    0.57
    med
    0.56
    ig
    0.56
    ate
    0.56
    va
    0.55
    POSITIVE LOGITS
     debates
    0.55
     LANGUAGES
    0.55
     ELECT
    0.50
     emocionante
    0.50
     অন্য
    0.49
     peces
    0.49
     presentes
    0.49
     UND
    0.49
     Canadá
    0.49
    PLACES
    0.48
    Act Density 0.000%

    No Known Activations