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

    Neuronpedia

    INDEX
    Explanations

    specialized data formats and syntactical elements

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

    Punctuation followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    special characters followed by code or urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .";
    -0.94
    存于互联网档案馆
    -0.85
    .",
    -0.83
    )».
    -0.80
    .")]
    -0.79
     GenerationType
    -0.79
    )»
    -0.79
    )");
    -0.78
     $_"
    -0.78
     handleMessage
    -0.78
    POSITIVE LOGITS
    ↵
    1.00
    <eos>
    0.98
    
    0.90
    ↵↵↵
    0.81
    0.74
    Content
    0.74
    ↵↵↵↵↵
    0.71
    ↵↵
    0.71
    
    0.70
    content
    0.69
    Act Density 0.424%

    No Known Activations