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

    Neuronpedia

    INDEX
    Explanations

    punctuation and pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ремон
    -0.07
     thờ
    -0.07
     NFL
    -0.06
     nationwide
    -0.06
     mnoh
    -0.06
    ;\
    -0.06
     alc
    -0.06
     participation
    -0.06
     Hab
    -0.06
    .OS
    -0.06
    POSITIVE LOGITS
    ्ग
    0.07
    黨
    0.07
     mammals
    0.06
    ύτε
    0.06
    애
    0.06
    -address
    0.06
    spi
    0.06
     ün
    0.06
     Sağ
    0.06
     utils
    0.06
    Act Density 0.001%

    No Known Activations