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

    Neuronpedia

    INDEX
    Explanations

    symbiotic, symlinks, sympathetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ен
    2.89
     subparagraph
    2.86
    कोर्ट
    2.80
    ี
    2.75
     bronchitis
    2.75
     রকম
    2.67
    ्यक्रम
    2.65
    seekBar
    2.64
     свят
    2.63
    unate
    2.61
    POSITIVE LOGITS
    ுள்ளார்
    3.14
    ுக்கு
    3.14
    ی
    3.09
    ਰ
    2.95
    le
    2.92
    ❖
    2.92
    𝙊
    2.91
    plectic
    2.88
    ுள்ளனர்
    2.73
    𝙉
    2.68
    Act Density 0.020%

    No Known Activations