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

    Neuronpedia

    INDEX
    Explanations

    segment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erv
    -0.08
     Lager
    -0.08
     baud
    -0.08
    悠
    -0.08
     embodied
    -0.08
     akk
    -0.08
    Reload
    -0.08
     현
    -0.08
     reload
    -0.08
     kijken
    -0.07
    POSITIVE LOGITS
     segmentation
    0.14
     deline
    0.11
     boundaries
    0.11
    seg
    0.10
    _boundary
    0.10
     clipping
    0.10
    _seg
    0.09
     contours
    0.09
    (seg
    0.09
    .seg
    0.09
    Act Density 0.007%

    No Known Activations