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

    Neuronpedia

    INDEX
    Explanations

    quadratic equations $ax^2+bx+c=0$

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ΠΑ
    0.45
    メイド
    0.42
    尧
    0.41
    ἅ
    0.41
     Townsend
    0.40
     Atmosphäre
    0.40
     OBD
    0.40
    国产
    0.39
    捅
    0.39
    ärte
    0.39
    POSITIVE LOGITS
     is
    0.47
     upang
    0.46
     sections
    0.43
     கொண்டுள்ளது
    0.42
    ita
    0.41
     пространства
    0.41
    others
    0.40
     toim
    0.40
    are
    0.40
     पुढे
    0.40
    Act Density 0.007%

    No Known Activations