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

    Neuronpedia

    INDEX
    Explanations

    segmentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    持ち
    -0.07
     pocházet
    -0.07
     DVD
    -0.06
    Fil
    -0.06
    Life
    -0.06
    ?>/
    -0.06
    Father
    -0.06
    Tour
    -0.06
     QHBoxLayout
    -0.06
     cost
    -0.06
    POSITIVE LOGITS
     segmentation
    0.09
     Cartesian
    0.07
     contexts
    0.07
     segreg
    0.07
     foreground
    0.06
     EB
    0.06
    .Unlock
    0.06
    Cong
    0.06
     sb
    0.06
    .Group
    0.06
    Act Density 0.005%

    No Known Activations