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

    Neuronpedia

    INDEX
    Explanations

    references to warnings and alerts

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

    "warning" or its variations

    np_acts-logits-general · gemini-2.0-flash

    warning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Verhältnisse
    -0.36
    onActivityResult
    -0.36
     BorderSide
    -0.36
     muuta
    -0.36
    Solución
    -0.35
    trabajo
    -0.35
     Ravi
    -0.34
     Relaciones
    -0.34
     dalamnya
    -0.33
    etree
    -0.33
    POSITIVE LOGITS
     warning
    2.50
     Warning
    2.30
     warnings
    2.27
    warning
    2.11
    Warning
    2.06
     warn
    2.03
     WARNING
    1.98
     warned
    1.98
     Warnings
    1.96
     warns
    1.94
    Act Density 0.101%

    No Known Activations