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

    Neuronpedia

    INDEX
    Explanations

    FastText model embeddings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    op
    0.67
    om
    0.61
    ?
    0.59
    ische
    0.58
    ya
    0.56
     ইত্যাদি
    0.56
    .
    0.56
    air
    0.56
    yn
    0.55
    ka
    0.55
    POSITIVE LOGITS
     تاکہ
    0.54
     Сурикова
    0.54
     रघु
    0.51
     jū
    0.50
    शत
    0.49
     decenas
    0.49
    了不少
    0.49
     dozens
    0.48
     టై
    0.47
    ⵛ
    0.47
    Act Density 0.000%

    No Known Activations