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

    Neuronpedia

    INDEX
    Explanations

    syntax-related elements in coding or programming contexts

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

    ending code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ebilir
    -0.44
     Suomessa
    -0.39
     brancas
    -0.39
     <<<<<<<<<<<<<<
    -0.39
     unknownFields
    -0.38
     inoxidable
    -0.38
     actuels
    -0.38
     disambiguazione
    -0.38
     vectorielles
    -0.37
     ProtoMessage
    -0.37
    POSITIVE LOGITS
    .",
    0.59
    ',
    0.58
    $',
    0.55
    ThroughAttribute
    0.55
    $__
    0.52
     ?";
    0.48
    .";
    0.48
    :");
    0.48
    >",
    0.48
    .[/
    0.47
    Act Density 0.033%

    No Known Activations