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

    Neuronpedia

    INDEX
    Explanations

    appearing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DE
    -0.06
    iculture
    -0.06
    uma
    -0.06
    .deck
    -0.06
    izens
    -0.06
    .pat
    -0.06
    Of
    -0.06
     Hava
    -0.06
     empathy
    -0.06
    VERS
    -0.06
    POSITIVE LOGITS
     SP
    0.07
     "<<
    0.07
    .↵↵↵↵↵
    0.06
     retarded
    0.06
     ignore
    0.06
    \',
    0.06
     parentheses
    0.06
    	throw
    0.06
     scrolled
    0.06
     nuanced
    0.06
    Act Density 0.001%

    No Known Activations