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

    Neuronpedia

    INDEX
    Explanations

    structuring lists around asterisks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     капу
    0.47
     عب
    0.44
    ストレ
    0.44
     табле
    0.44
     subtracted
    0.43
    capacitor
    0.43
    constexpr
    0.43
    Пи
    0.42
     косми
    0.41
    vive
    0.41
    POSITIVE LOGITS
     Deck
    0.47
     disinfecting
    0.45
    ający
    0.44
    meyer
    0.44
    它
    0.44
     Beer
    0.43
     KeyError
    0.43
    רון
    0.42
    痪
    0.42
     เว
    0.42
    Act Density 0.007%

    No Known Activations