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

    Neuronpedia

    INDEX
    Explanations

    years followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ד
    0.62
    сть
    0.54
    レー
    0.52
    د
    0.50
    ामध्ये
    0.49
    тину
    0.49
    ム
    0.48
    츠
    0.48
    ני
    0.48
    λα
    0.48
    POSITIVE LOGITS
     OF
    0.61
     Indien
    0.61
     of
    0.60
     THE
    0.59
     et
    0.59
     AB
    0.58
     ANTI
    0.58
     annen
    0.57
     ID
    0.56
     I
    0.56
    Act Density 0.881%

    No Known Activations