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

    Neuronpedia

    INDEX
    Explanations

    closing braces and semicolons in code structures

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

    Code snippets or code-related terms

    np_acts-logits-general · gemini-2.0-flash

    code block endings or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -0.93
     InputDecoration
    -0.91
     Houſe
    -0.85
     Савезне
    -0.85
     Majefty
    -0.83
     '\\;'
    -0.83
     Chriftian
    -0.82
     BoxDecoration
    -0.81
    SerializedSize
    -0.81
     myſelf
    -0.81
    POSITIVE LOGITS
    ↵↵
    0.75
    <eos>
    0.57
     function
    0.53
     et
    0.48
    ↵
    0.47
     Ad
    0.46
    function
    0.46
    шої
    0.45
    </blockquote>
    0.45
     esta
    0.44
    Act Density 0.131%

    No Known Activations