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

    Neuronpedia

    INDEX
    Explanations

    Sets and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     অব
    -0.09
    (sz
    -0.08
     funcionários
    -0.08
    elizmente
    -0.08
     neden
    -0.08
     fj
    -0.08
    還
    -0.08
     Ruhe
    -0.08
    sle
    -0.08
     piso
    -0.07
    POSITIVE LOGITS
    Overlap
    0.14
     overlaps
    0.14
     overlap
    0.13
     overlapping
    0.12
     intersects
    0.11
    _overlap
    0.10
     intersect
    0.10
    Some
    0.09
     overlays
    0.09
    Contains
    0.09
    Act Density 0.070%

    No Known Activations