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

    Neuronpedia

    INDEX
    Explanations

    lists and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Heather
    0.52
    ausal
    0.47
     ti
    0.46
    éral
    0.44
    Heather
    0.43
    认真
    0.42
     Yon
    0.41
     heather
    0.41
     對
    0.41
    hhhhhhhh
    0.40
    POSITIVE LOGITS
    </sup>
    0.50
    IMP
    0.50
     وفق
    0.48
    shop
    0.47
    ЕТ
    0.46
    ЕМ
    0.46
     encomendas
    0.45
     головы
    0.45
     gibi
    0.44
     ناقص
    0.44
    Act Density 0.006%

    No Known Activations