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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     бороть
    -0.07
    Shield
    -0.06
     mascot
    -0.06
     تول
    -0.06
    -bel
    -0.06
    ﾉ
    -0.06
    ثمان
    -0.06
     문화
    -0.06
     рублей
    -0.06
    tolower
    -0.06
    POSITIVE LOGITS
    mma
    0.07
    г
    0.06
     casino
    0.06
     귀
    0.06
     '"+
    0.06
     noises
    0.06
    (Py
    0.06
     affirm
    0.06
     promises
    0.06
    ife
    0.06
    Act Density 0.002%

    No Known Activations