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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sprawling
    -0.06
    python
    -0.06
     Québec
    -0.06
    chk
    -0.06
    needs
    -0.06
    星
    -0.06
    evento
    -0.06
     seating
    -0.06
     nk
    -0.05
     western
    -0.05
    POSITIVE LOGITS
    -,
    0.09
    ्ध
    0.07
    -gr
    0.07
    !!}</
    0.07
    filePath
    0.07
    -you
    0.07
    лых
    0.07
    !
    0.06
    /uploads
    0.06
    .integer
    0.06
    Act Density 0.012%

    No Known Activations