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

    Neuronpedia

    INDEX
    Explanations

    percentage-related formatting in the document

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

    percentage followed by border or opposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     new
    -0.48
    -
    -0.43
    s
    -0.39
    2
    -0.39
    _
    -0.38
     reducido
    -0.36
    add
    -0.35
    :
    -0.35
     =
    -0.35
     “
    -0.35
    POSITIVE LOGITS
    %";
    1.10
    %',
    1.06
    %",
    1.05
    %;
    1.04
     $_"
    1.02
     \%,
    0.98
    %");
    0.98
     \%$\\
    0.97
    %;
    0.96
     \%$
    0.96
    Act Density 0.004%

    No Known Activations