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

    Neuronpedia

    INDEX
    Explanations

    make mistakes, sex with you, make your own

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    it
    0.26
    বাধিকার
    0.25
     elk
    0.24
    ध
    0.23
    ć
    0.23
    当
    0.23
    রত
    0.23
    0.23
    ع
    0.23
     lanthan
    0.23
    POSITIVE LOGITS
     menudo
    0.23
    НИЕ
    0.22
     iler
    0.22
    ्वती
    0.21
     goTo
    0.21
    dozen
    0.20
     pukul
    0.20
     пока
    0.20
    iculty
    0.20
     Millionen
    0.20
    Act Density 0.228%

    No Known Activations