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

    Neuronpedia

    INDEX
    Explanations

    key questions and frameworks for understanding various topics

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

    seeking definitions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.86
    adaptiveStyles
    -0.76
     queſta
    -0.76
    RTLR
    -0.72
     betweenstory
    -0.71
    tinyos
    -0.68
    expandindo
    -0.67
     CreateTagHelper
    -0.67
    Personensuche
    -0.66
    Sucesor
    -0.65
    POSITIVE LOGITS
     definition
    0.34
     explained
    0.31
    Definition
    0.31
     defin
    0.30
     kennen
    0.30
    定义
    0.29
     defines
    0.29
    expliquer
    0.29
     explaining
    0.29
    Presented
    0.29
    Act Density 0.037%

    No Known Activations