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

    Neuronpedia

    INDEX
    Explanations

    volume and issue numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    純正
    0.72
     اظهار
    0.72
     좋은
    0.71
     अच्छ
    0.69
    洹
    0.68
     লেখাপ
    0.68
     파일
    0.67
     다시
    0.65
    人形
    0.65
     fles
    0.65
    POSITIVE LOGITS
    (
    0.95
    Issue
    0.92
    Volume
    0.90
     Volume
    0.83
     Nr
    0.83
    Supplement
    0.82
    Vol
    0.82
     vol
    0.81
    ():
    0.79
    óa
    0.79
    Act Density 0.030%

    No Known Activations