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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tep
    -0.07
    girls
    -0.07
    富豪
    -0.07
     dáng
    -0.07
     tantra
    -0.07
    pga
    -0.07
    ❧
    -0.07
    pee
    -0.07
    aidu
    -0.07
    aining
    -0.07
    POSITIVE LOGITS
    产学
    0.07
    >";
    0.07
    ;
    0.07
     להש
    0.07
    Inter
    0.07
    𬌗
    0.07
    ":"'
    0.07
    [int
    0.07
    防控
    0.07
    运
    0.07
    Act Density 0.006%

    No Known Activations