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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and their associated roles or titles in a structured context

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

    titles and official positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тистика
    -0.34
    +#+#
    -0.32
    FXMLLoader
    -0.32
    Хьажоргаш
    -0.31
    toplankton
    -0.30
    Diweddarwch
    -0.30
     piratas
    -0.29
    史
    -0.29
     intStringLen
    -0.27
     conco
    -0.27
    POSITIVE LOGITS
    zitter
    0.61
    CodeAttribute
    0.56
     chofe
    0.54
     ControllerBase
    0.54
    Director
    0.54
     Director
    0.54
    RTDA
    0.54
     handleClick
    0.54
     Chairman
    0.53
     Chair
    0.52
    Act Density 0.018%

    No Known Activations