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

    Neuronpedia

    INDEX
    Explanations

    向 + receiver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    1.14
    ت
    0.85
    ن
    0.85
    ك
    0.82
    のための
    0.80
    のリ
    0.77
    的要求
    0.77
    的分
    0.74
    ام
    0.71
    の為
    0.70
    POSITIVE LOGITS
     it
    0.77
    RELL
    0.71
    Roll
    0.71
    Logan
    0.68
    VILLE
    0.67
    Garcia
    0.67
    RELATES
    0.66
    Hughes
    0.65
    SYS
    0.65
    त्रेयी
    0.65
    Act Density 0.000%

    No Known Activations