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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yeni
    -0.07
    很多
    -0.07
     escaped
    -0.07
     خدا
    -0.06
    Provid
    -0.06
    와
    -0.06
    yang
    -0.06
     cards
    -0.06
     büyük
    -0.06
     Anda
    -0.06
    POSITIVE LOGITS
     Rolled
    0.07
     McC
    0.06
     monoc
    0.06
    //--------------------------------------------------------------↵
    0.06
    сть
    0.06
     مسئله
    0.06
    FXML
    0.06
    ันท
    0.06
    -dem
    0.06
     mnemonic
    0.06
    Act Density 0.007%

    No Known Activations