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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    深交
    -0.08
    睫
    -0.07
    gements
    -0.07
    (Program
    -0.07
    �
    -0.07
    -ch
    -0.07
     HEALTH
    -0.07
    Խ
    -0.07
    股民
    -0.07
    導
    -0.07
    POSITIVE LOGITS
     concatenated
    0.07
     phot
    0.07
    dns
    0.07
     synthes
    0.07
    AccessToken
    0.07
     bottle
    0.07
     TSR
    0.07
     INSERT
    0.07
     setValue
    0.07
    [col
    0.07
    Act Density 0.019%

    No Known Activations