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

    Neuronpedia

    INDEX
    Explanations

    categorized by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ٫
    0.89
    非常
    0.87
     ถูก
    0.84
    ،
    0.81
    有一个
    0.80
    ;
    0.80
    مره
    0.79
     כך
    0.78
     จาก
    0.78
    有一种
    0.78
    POSITIVE LOGITS
     অদ
    0.81
     presumably
    0.78
     hopefully
    0.78
     perhaps
    0.72
     gär
    0.69
     gleaned
    0.69
     magari
    0.69
    klady
    0.68
     conceivably
    0.68
     മാത്രം
    0.67
    Act Density 0.152%

    No Known Activations