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

    Neuronpedia

    INDEX
    Explanations

    dialogue markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desliz
    0.44
     samtidig
    0.44
     جنہوں
    0.43
     uyg
    0.43
     conjuntos
    0.42
     astfel
    0.41
     cikin
    0.41
    그러
    0.40
     दवाओं
    0.40
     infarction
    0.40
    POSITIVE LOGITS
    你要
    0.50
    quee
    0.49
     academically
    0.48
    9
    0.48
    oh
    0.47
    itize
    0.44
    如果你
    0.44
    ipari
    0.44
    Y
    0.43
    8
    0.43
    Act Density 0.008%

    No Known Activations