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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thousands
    0.91
    <b>
    0.89
     सैकड़ों
    0.84
    <i>
    0.82
    hundred
    0.82
     چندین
    0.81
    तीन
    0.80
     dozens
    0.80
    Hundreds
    0.79
    <strong>
    0.78
    POSITIVE LOGITS
    2.69
     ۸
    1.66
     ۶
    1.65
     ۴
    1.63
     ۹
    1.63
     ۵
    1.63
     ١
    1.59
     ۷
    1.59
     ٢
    1.56
     ٣
    1.49
    Act Density 1.170%

    No Known Activations