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

    Neuronpedia

    INDEX
    Explanations

    references to results and outcomes in data or programming contexts

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

    code blocks and math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.91
     estekak
    -0.74
    rungsseite
    -0.73
     ویکی‌پدی
    -0.68
    ViewImports
    -0.68
     propOrder
    -0.67
    httphttps
    -0.67
     defaultstate
    -0.66
    Hentet
    -0.64
    CppMethod
    -0.61
    POSITIVE LOGITS
    AutoModerator
    0.37
     bâton
    0.34
     Administração
    0.33
     Geduld
    0.32
     bambou
    0.31
    暦
    0.31
    izowane
    0.31
    ísimo
    0.31
     concreto
    0.31
     Unión
    0.30
    Act Density 0.127%

    No Known Activations