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

    Neuronpedia

    INDEX
    Explanations

    ratings and difficulty levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ！！
    0.44
    ಗಳಿವೆ
    0.40
    ग्राम
    0.40
    !।
    0.39
    Խ
    0.39
    ដែលមាន
    0.39
     通常
    0.38
     両
    0.38
    はその
    0.38
    ！
    0.38
    POSITIVE LOGITS
    يمة
    0.44
     the
    0.38
     and
    0.37
     reminding
    0.36
     a
    0.34
    Mont
    0.34
    and
    0.34
     okay
    0.34
     Gary
    0.34
    এবং
    0.34
    Act Density 0.059%

    No Known Activations