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

    Neuronpedia

    INDEX
    Explanations

    money, items, or obligations owed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ஂ
    -2.95
    </tfoot>
    -2.81
    ;
    -2.73
    </i>
    -2.72
    żeli
    -2.63
    }(
    -2.56
    ");
    -2.48
    聍
    -2.41
    ਃ
    -2.38
    Ꭳ
    -2.30
    POSITIVE LOGITS
    </strong>
    2.45
     
    2.39
    ↵↵
    2.33
    ができる
    2.08
     Keine
    2.02
    the
    1.98
     Secrétaire
    1.98
     Siehe
    1.91
    '
    1.90
     Beſ
    1.86
    Act Density 0.002%

    No Known Activations