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

    Neuronpedia

    INDEX
    Explanations

    smooth texture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いた
    2.34
    ं
    2.28
    부터
    2.25
    ം
    2.06
    ้
    2.05
    니다
    1.92
    ం
    1.89
    cular
    1.88
    сть
    1.85
    tı
    1.72
    POSITIVE LOGITS
    ۳
    1.78
    Ε
    1.72
    ጠን
    1.71
    ۵
    1.69
     sacraments
    1.66
    ﯽ
    1.66
     secreted
    1.66
    此事
    1.63
    ۴
    1.63
    स
    1.61
    Act Density 0.007%

    No Known Activations