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

    Neuronpedia

    INDEX
    Explanations

    menstruation, minimum safe, accurate initial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    日志
    0.47
    慵
    0.45
     سهل
    0.42
    启发
    0.42
     ගැන
    0.42
     低
    0.42
     saddhim
    0.42
     yielded
    0.41
    ophiles
    0.40
     Enzym
    0.40
    POSITIVE LOGITS
    И
    0.44
    0.43
     cough
    0.39
     rostrum
    0.39
     word
    0.38
    Alam
    0.38
    Very
    0.37
    uelve
    0.37
    ้อม
    0.37
    Word
    0.36
    Act Density 0.000%

    No Known Activations