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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    birth
    -0.07
    ipers
    -0.07
    Prot
    -0.07
    udd
    -0.07
     adapters
    -0.07
    អ
    -0.07
    Kon
    -0.07
     allure
    -0.07
     arty
    -0.07
    eting
    -0.06
    POSITIVE LOGITS
    FTER
    0.07
    뿐만
    0.07
     heartfelt
    0.07
    ᠮ
    0.07
    常に
    0.07
    ddy
    0.07
    덤
    0.07
    园林
    0.07
    的行为
    0.07
    hexdigest
    0.07
    Act Density 0.004%

    No Known Activations