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

    Neuronpedia

    INDEX
    Explanations

    warnings and notices about possible risks or issues

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

    warnings or being warned

    np_acts-logits-general · gemini-2.0-flash

    issuing a warning or notice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蚪
    -0.33
    ContentAsync
    -0.32
    ExecuteReader
    -0.32
    Solución
    -0.31
    COMMIT
    -0.30
     butterknife
    -0.30
    BagLayout
    -0.30
     AssemblyCompany
    -0.29
    ABAJO
    -0.29
    antwoorden
    -0.29
    POSITIVE LOGITS
     warning
    2.83
     warnings
    2.55
     warn
    2.42
     Warning
    2.30
     warned
    2.30
    warning
    2.22
     warns
    2.17
     Warnings
    2.13
    警告
    2.11
    Warning
    2.05
    Act Density 0.562%

    No Known Activations