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

    Neuronpedia

    INDEX
    Explanations

    instances of formatting symbols and whitespace in code snippets

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

    Code snippets or file headers

    np_acts-logits-general · gemini-2.0-flash

    python `self` keyword

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.74
    :+:
    -0.69
     ddelweddau
    -0.68
    argout
    -0.66
     surla
    -0.64
     uVar
    -0.61
    RTLD
    -0.61
     useRef
    -0.61
     onAnimation
    -0.61
     FetchType
    -0.60
    POSITIVE LOGITS
    GEBURTS
    0.65
    <eos>
    0.62
    tagHelperRunner
    0.54
     polymorphism
    0.51
     polymorphisms
    0.47
     exemplo
    0.47
     ballerina
    0.46
     habitable
    0.46
     дописавши
    0.45
     mobilisation
    0.44
    Act Density 0.082%

    No Known Activations