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

    Neuronpedia

    INDEX
    Explanations

    financial debt, physical exam

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يا
    1.27
    يل
    1.16
    كي
    1.13
    kých
    1.06
    さ
    1.06
    ك
    0.97
    kę
    0.96
    ků
    0.96
    ký
    0.96
    两
    0.96
    POSITIVE LOGITS
    the
    1.16
    ר
    1.13
    ر
    1.02
    in
    1.00
    at
    0.92
    to
    0.91
    they
    0.87
    ०
    0.86
    ுள்ளார்
    0.86
    s
    0.85
    Act Density 0.776%

    No Known Activations