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

    Neuronpedia

    INDEX
    Explanations

    rankings and ties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BOM
    -0.08
     фер
    -0.08
    _ANAL
    -0.08
     LOL
    -0.08
     перспектив
    -0.08
    ಲನ
    -0.08
    ೋದ
    -0.08
     hemis
    -0.08
     lík
    -0.07
     liquor
    -0.07
    POSITIVE LOGITS
     duplicates
    0.11
    duplicates
    0.10
    _duplicate
    0.10
    _duplicates
    0.10
    Duplicates
    0.10
     ties
    0.10
    Equality
    0.10
    duplicate
    0.09
     equality
    0.09
     duplicate
    0.09
    Act Density 0.015%

    No Known Activations