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

    Neuronpedia

    INDEX
    Explanations

    locations and directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	name
    -0.07
     appended
    -0.06
    _ad
    -0.06
     Ng
    -0.06
    _ITER
    -0.06
     estado
    -0.06
     Manus
    -0.06
     ledger
    -0.06
    Wed
    -0.06
     quotes
    -0.06
    POSITIVE LOGITS
    .ra
    0.07
     дані
    0.07
    ‌های
    0.07
     vå
    0.07
     ['./
    0.07
     SolidColorBrush
    0.06
    щі
    0.06
     disp
    0.06
    (best
    0.06
     À
    0.06
    Act Density 0.015%

    No Known Activations