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

    Neuronpedia

    INDEX
    Explanations

    the one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ش
    3.02
    نا
    2.55
    د
    2.47
    א
    2.36
    ।
    2.19
    ا
    2.13
    الأ
    2.08
    나
    2.08
    ۔
    2.00
    ৪
    2.00
    POSITIVE LOGITS
    씩
    1.59
    вой
    1.55
     Medications
    1.52
     এদিকে
    1.50
    ota
    1.46
    ức
    1.46
     conten
    1.45
    াকী
    1.44
     vehemently
    1.44
    Fonte
    1.43
    Act Density 0.169%

    No Known Activations