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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    inals
    -0.25
    Certain
    -0.25
    ophobic
    -0.24
    mighty
    -0.24
    éĴµ
    -0.24
    ạch
    -0.23
    éĨĴ
    -0.23
    eb
    -0.23
    å²ģ以ä¸ĭ
    -0.22
    ÑģÑĤвенно
    -0.22
    POSITIVE LOGITS
    (compact
    0.26
    andex
    0.24
    lian
    0.23
    á»ı
    0.23
    afil
    0.23
    -publish
    0.23
    IGO
    0.23
    yg
    0.22
    afa
    0.22
     gig
    0.22
    Act Density 0.019%

    No Known Activations

    This feature has no known activations.