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

    Neuronpedia

    INDEX
    Explanations

    special characters and their relationships in structured data

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

    Mathematical or programming expressions with parentheses and symbols

    np_acts-logits-general · gemini-2.0-flash

    selected option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nexo
    -0.73
     Иль
    -0.70
     
    -0.68
     General
    -0.65
    riwal
    -0.62
    able
    -0.60
     L
    -0.58
    avía
    -0.58
     E
    -0.57
    findpost
    -0.56
    POSITIVE LOGITS
     للمعارف
    1.27
    (!__
    0.91
     ${({
    0.90
    SequentialGroup
    0.89
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.87
    ","","
    0.84
    (`${
    0.84
    )..
    0.83
    原始内容存档于
    0.83
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.82
    Act Density 0.415%

    No Known Activations