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

    Neuronpedia

    INDEX
    Explanations

    nation's, country's, user's, brother's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     соответствии
    0.91
    යක්
    0.89
    මක්
    0.83
    环境下
    0.82
    ্ু
    0.80
     '',
    0.79
    、『
    0.78
    isiaj
    0.76
    Hochspringen
    0.76
    வ்வாறு
    0.76
    POSITIVE LOGITS
    '
    3.19
    ’
    3.10
    ´
    2.16
     యొక్క
    2.02
    의
    1.97
    യുടെ
    1.97
    த்தின்
    1.85
    ரின்
    1.84
    들의
    1.80
    \'
    1.79
    Act Density 0.858%

    No Known Activations