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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confection
    -0.09
    袋
    -0.08
    PAD
    -0.08
     recycled
    -0.08
     Aldi
    -0.08
     rem
    -0.07
     fundraising
    -0.07
     hưởng
    -0.07
     Nana
    -0.07
     verdienen
    -0.07
    POSITIVE LOGITS
     جلوگیری
    0.10
     предотвращ
    0.10
     Prevention
    0.09
     impedir
    0.09
     prevent
    0.09
     Ass
    0.09
     prevention
    0.09
     assumption
    0.09
     prevents
    0.09
    Prevent
    0.09
    Act Density 0.026%

    No Known Activations