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

    Neuronpedia

    INDEX
    Explanations

    FOR IMMEDIATE RELEASE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     মাত্রা
    0.49
     LOCCTR
    0.48
     суме
    0.48
     Ciò
    0.46
     melakukannya
    0.46
     มัน
    0.46
     neurotrans
    0.46
     វា
    0.45
     ஏற்படுகிறது
    0.45
     "?"
    0.45
    POSITIVE LOGITS
    修改
    0.49
    श
    0.45
    ：
    0.44
    êt
    0.43
    2
    0.43
    版本
    0.42
    视频
    0.41
     raffle
    0.41
     December
    0.41
     reprint
    0.41
    Act Density 0.000%

    No Known Activations