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

    Neuronpedia

    INDEX
    Explanations

    aspects related to programming structures and elements in code snippets

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

    constructor-arg name type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Comprometido
    -0.44
     vandens
    -0.40
     permasalahan
    -0.40
     Sloveniji
    -0.40
     binatang
    -0.40
     dianggap
    -0.40
    posób
    -0.40
     alrededores
    -0.40
     kaksi
    -0.40
     informatique
    -0.39
    POSITIVE LOGITS
    EndContext
    0.65
    InputBorder
    0.57
    UserScript
    0.57
     betweenstory
    0.56
    xnn
    0.54
     CanadaChoose
    0.52
    parsedMessage
    0.51
     للاسماء
    0.51
    twimg
    0.50
    -',
    0.50
    Act Density 0.138%

    No Known Activations