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

    Neuronpedia

    INDEX
    Explanations

    Los

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Daniels
    -0.07
     shuffled
    -0.07
    Folders
    -0.06
    dg
    -0.06
    _trip
    -0.06
     Rei
    -0.06
    .enter
    -0.06
    Dlg
    -0.06
     antibiotics
    -0.06
     Swamp
    -0.06
    POSITIVE LOGITS
    ?>"/>↵
    0.08
    does
    0.07
    .iloc
    0.07
     ALWAYS
    0.07
    من
    0.06
    legant
    0.06
     IRC
    0.06
     isError
    0.06
    .toLocale
    0.06
     lasc
    0.06
    Act Density 0.003%

    No Known Activations