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

    Neuronpedia

    INDEX
    Explanations

    technical terms and data structures

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

    Code, symbols, or European punctuation

    np_acts-logits-general · gemini-2.0-flash

    code syntax and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()")
    -1.10
    ()");
    -1.04
    ]");
    -1.04
    %")
    -1.00
    >")
    -0.98
    )");
    -0.98
    )”.
    -0.97
    }")
    -0.96
    '")
    -0.95
    ')))
    -0.95
    POSITIVE LOGITS
    ，
    0.58
    ormais
    0.56
     ،
    0.56
     ...
    0.56
    0.56
    ,
    0.54
     conseguenza
    0.54
    ícil
    0.53
    rean
    0.52
     morire
    0.52
    Act Density 0.097%

    No Known Activations