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

    Neuronpedia

    INDEX
    Explanations

    (V

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     afflicted
    -0.08
    oken
    -0.07
    SE
    -0.07
    igor
    -0.07
     Paperback
    -0.07
     painters
    -0.06
    ertino
    -0.06
    _PROJECT
    -0.06
     Marble
    -0.06
    .inline
    -0.06
    POSITIVE LOGITS
    .svg
    0.07
    .IsTrue
    0.06
    .property
    0.06
     shoulders
    0.06
     materi
    0.06
     marque
    0.06
     は
    0.06
     differential
    0.06
     jump
    0.06
    icopt
    0.05
    Act Density 0.019%

    No Known Activations