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

    Neuronpedia

    INDEX
    Explanations

    Bachelor's degree requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ק
    1.17
    の
    1.01
    いき
    1.00
    માં
    0.98
    지
    0.96
    いずれ
    0.95
    ע
    0.90
    بد
    0.89
    いった
    0.86
    いますが
    0.86
    POSITIVE LOGITS
    ↵
    1.02
    il
    0.88
    ↵↵
    0.86
    <0x0D>
    0.83
    ărilor
    0.82
    ont
    0.80
    </td>
    0.79
    ’
    0.79
    ra
    0.77
    in
    0.77
    Act Density 0.004%

    No Known Activations