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

    Neuronpedia

    INDEX
    Explanations

    brackets and parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Basically
    -0.08
    `);↵↵
    -0.07
     ''){↵
    -0.07
    \"",
    -0.07
    ~↵
    -0.07
    ');?>
    -0.07
     (~(
    -0.07
     Reflection
    -0.07
    __)↵↵↵
    -0.07
    );\
    -0.07
    POSITIVE LOGITS
    �
    0.08
    wchar
    0.07
    vanished
    0.07
    stituição
    0.07
    .chart
    0.07
    onus
    0.07
     subordinate
    0.07
    ён
    0.07
     plural
    0.07
    itre
    0.07
    Act Density 0.087%

    No Known Activations