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

    Neuronpedia

    INDEX
    Explanations

    geometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foil
    -0.07
    attis
    -0.07
     Аз
    -0.07
     അന്ത
    -0.07
    ാവ
    -0.07
    ाला
    -0.07
    858
    -0.06
    odzie
    -0.06
    zah
    -0.06
    -loop
    -0.06
    POSITIVE LOGITS
     overlapping
    0.12
     overlaps
    0.10
    Overlap
    0.10
     overlap
    0.10
     individuales
    0.10
    _overlap
    0.10
     individually
    0.09
    pheres
    0.09
    Intersect
    0.09
     rectangles
    0.09
    Act Density 0.030%

    No Known Activations