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

    Neuronpedia

    INDEX
    Explanations

    function definitions and method calls in programming code

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

    Bit shifting operations involving "S" and "M"

    np_acts-logits-general · gemini-2.0-flash

    C/C++ preprocessor `#define` statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.76
     Geſch
    -0.73
    wiliwch
    -0.71
     мәкал
    -0.71
    iſen
    -0.70
     ब्रेकडाउन
    -0.70
    ſammen
    -0.69
    neté
    -0.69
    ſſung
    -0.69
    majánló
    -0.68
    POSITIVE LOGITS
    pres
    0.37
    ↵
    0.37
    ↵↵
    0.36
      
    0.36
     b
    0.35
    ↵↵↵
    0.35
     means
    0.33
     here
    0.33
     Friendly
    0.32
    手
    0.32
    Act Density 0.217%

    No Known Activations