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

    Neuronpedia

    INDEX
    Explanations

    numbers and parentheses in citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䣫
    0.40
    Imidazole
    0.39
    রত্ব
    0.39
     backlit
    0.39
    醀
    0.38
    㳑
    0.38
     সক্রিয়
    0.38
    퇸
    0.38
    活性
    0.38
    ాలయ
    0.38
    POSITIVE LOGITS
    5
    0.56
    8
    0.54
    6
    0.54
     (
    0.53
    7
    0.51
     [
    0.50
    9
    0.50
    ;
    0.49
    4
    0.48
    3
    0.48
    Act Density 0.001%

    No Known Activations