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

    Neuronpedia

    INDEX
    Explanations

    novel beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ffineTransform
    0.46
    敚
    0.44
    ূতন
    0.42
    чаем
    0.42
    쯜
    0.42
    FreeFlag
    0.42
     calcareous
    0.41
    చిన
    0.41
    atience
    0.40
    ٹے
    0.40
    POSITIVE LOGITS
    0.50
     国内
    0.44
     Rumble
    0.44
    ！！！
    0.44
     बेहतरीन
    0.43
     🔥
    0.43
    ！！
    0.42
    NEW
    0.42
    !
    0.42
    轰
    0.42
    Act Density 0.002%

    No Known Activations