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

    Neuronpedia

    INDEX
    Explanations

    defined roles or characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    0.51
     몇
    0.46
     ಚಿ
    0.45
    Tao
    0.43
    லாம்
    0.42
    老
    0.42
    说什么
    0.42
     Tao
    0.41
     δὲ
    0.41
     خطا
    0.40
    POSITIVE LOGITS
    organiz
    0.47
     diastere
    0.47
    domain
    0.46
    acity
    0.43
     mainland
    0.43
     spese
    0.42
     DS
    0.41
    -
    0.41
     wastewater
    0.41
     demain
    0.41
    Act Density 0.008%

    No Known Activations