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

    Neuronpedia

    INDEX
    Explanations

    code element endings;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jeff
    0.73
     czter
    0.73
    ား
    0.73
     Zusch
    0.71
     ढेर
    0.71
    IMS
    0.71
    ру
    0.70
    ަލ
    0.70
    ુલ
    0.70
    ২৯
    0.70
    POSITIVE LOGITS
    ;
    1.08
    ";
    1.07
    ");
    1.07
    ”;
    1.06
    ’;
    1.03
    ；
    1.00
    .";
    1.00
    »;
    0.92
    \";
    0.92
    /
    0.92
    Act Density 0.074%

    No Known Activations