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

    Neuronpedia

    INDEX
    Explanations

    parentheses and single quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .find
    -0.07
    :
    -0.07
    okay
    -0.07
     알고
    -0.06
    .preventDefault
    -0.06
    'nun
    -0.06
    ';';
    -0.06
     ノ
    -0.06
     facilitated
    -0.06
     '%
    -0.06
    POSITIVE LOGITS
     복
    0.07
    ')}}">
    0.06
     cà
    0.06
     输
    0.06
     instantiated
    0.06
     central
    0.06
    ères
    0.06
    .Master
    0.06
     Değer
    0.06
     femin
    0.06
    Act Density 0.108%

    No Known Activations