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

    Neuronpedia

    INDEX
    Explanations

    for loop start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tất
    0.78
     urt
    0.77
     all
    0.76
    সকল
    0.72
    sizeof
    0.72
    جميع
    0.71
     Semua
    0.69
    imped
    0.68
    étr
    0.68
     എല്ലാവ
    0.67
    POSITIVE LOGITS
     👇
    0.73
    ꯔ
    0.70
    addContainerGap
    0.65
     décider
    0.65
     placés
    0.64
     divide
    0.64
     tacked
    0.64
     varied
    0.63
    ())+
    0.63
     કામ
    0.63
    Act Density 0.001%

    No Known Activations