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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to statistical analysis and modeling

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

    Text following headings or titles

    np_acts-logits-general · gemini-2.0-flash

    section headings and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.45
    "):
    -1.41
    ')):
    -1.37
     дописавши
    -1.35
    )");
    -1.34
    )";
    -1.33
    NUMX
    -1.32
    '));
    -1.29
    '):
    -1.29
     Audiodateien
    -1.28
    POSITIVE LOGITS
    _
    1.85
    \_
    1.26
    __
    1.10
    -
    1.03
    %
    0.83
    _{
    0.79
     _
    0.77
    +
    0.77
    @
    0.72
    /
    0.72
    Act Density 1.224%

    No Known Activations