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

    Neuronpedia

    INDEX
    Explanations

    overlap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fri
    -0.09
    INTEGER
    -0.08
     ferrament
    -0.08
     Körper
    -0.08
     المقاومة
    -0.07
     corporal
    -0.07
     Fri
    -0.07
     lichaams
    -0.07
     Chap
    -0.07
    sel
    -0.07
    POSITIVE LOGITS
     overlapping
    0.17
     overlap
    0.16
     overlaps
    0.15
    Overlap
    0.15
    _overlap
    0.13
     overl
    0.11
    lapping
    0.09
     공유
    0.09
     overwrite
    0.08
     recycle
    0.08
    Act Density 0.019%

    No Known Activations