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

    Neuronpedia

    INDEX
    Explanations

    qualities with or without

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilarly
    0.42
    เพื่อให้
    0.41
     nhằm
    0.38
    अभ
    0.37
     APIDC
    0.36
     funkcjon
    0.36
    बीसी
    0.36
     żeby
    0.36
    níků
    0.36
    нкт
    0.36
    POSITIVE LOGITS
     without
    0.69
     sambil
    0.69
     while
    0.63
     tanpa
    0.61
     Without
    0.58
     بدون
    0.57
     with
    0.57
    的同时
    0.57
     плюс
    0.57
    while
    0.56
    Act Density 0.017%

    No Known Activations