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

    Neuronpedia

    INDEX
    Explanations

    the closing curly brace characters in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code and logic syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    protoc
    -0.62
     المعيارى
    -0.48
     Comics
    -0.46
    richTextPanel
    -0.46
    oredCriteria
    -0.45
     صوتيه
    -0.45
    XtraReports
    -0.45
     Drawable
    -0.44
    простра
    -0.43
    omock
    -0.43
    POSITIVE LOGITS
    er
    0.77
    erà
    0.54
    erii
    0.52
    };
    0.47
    };*/
    0.47
    ()};
    0.46
    //};
    0.46
    }],
    0.46
    jenigen
    0.46
    ../
    0.46
    Act Density 0.033%

    No Known Activations