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

    Neuronpedia

    INDEX
    Explanations

    elements related to visual data presentation, such as figures and graphs

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

    File extensions for image formats

    np_acts-logits-general · gemini-2.0-flash

    image file extensions in figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    saraba
    -0.88
    ArrowToggle
    -0.80
     BorderRadius
    -0.76
    ########.
    -0.75
    protoimpl
    -0.75
    AsUp
    -0.73
     '\\;'
    -0.72
    exitRule
    -0.72
    GeneratedCode
    -0.72
     Lijst
    -0.72
    POSITIVE LOGITS
    </code>
    0.67
    </h1>
    0.63
    </h4>
    0.63
    </blockquote>
    0.63
    </h2>
    0.61
    ↵
    0.59
    </h5>
    0.59
    0.57
    ↵↵↵
    0.56
    }
    0.56
    Act Density 0.035%

    No Known Activations