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

    Neuronpedia

    INDEX
    Explanations

    technical syntax and symbols related to programming or data structures

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

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.49
    ########.
    -0.44
    KommentareTeilen
    -0.40
    __;
    -0.39
    )))),
    -0.39
    ))),
    -0.39
    Халык
    -0.38
    FECTION
    -0.38
    %)$
    -0.38
    ++);
    -0.38
    POSITIVE LOGITS
    ViewImports
    0.61
     snippetHide
    0.50
    ViewFeatures
    0.44
    BagLayout
    0.43
    corazón
    0.43
    DIPSETTING
    0.42
     ComVisible
    0.41
    knee
    0.40
     voies
    0.38
    SystemColors
    0.38
    Act Density 0.001%

    No Known Activations