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

    Neuronpedia

    INDEX
    Explanations

    code license headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    afd
    -0.07
    gef
    -0.06
     Pac
    -0.06
     transforming
    -0.06
    TextBoxColumn
    -0.06
    蜷
    -0.06
     спе
    -0.06
    跺
    -0.06
    apr
    -0.06
    =<
    -0.06
    POSITIVE LOGITS
    郪
    0.07
    tracks
    0.07
    _costs
    0.07
    혼
    0.07
    _KIND
    0.07
    妓
    0.06
    pipeline
    0.06
    specified
    0.06
     noticing
    0.06
    瑛
    0.06
    Act Density 0.001%

    No Known Activations