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

    Neuronpedia

    INDEX
    Explanations

    scenarios involving system failures or outages

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

    potential issues or failures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.59
    IBOutlet
    -0.45
     Völker
    -0.38
    enoord
    -0.37
    GOTREF
    -0.35
     halten
    -0.34
     modern
    -0.33
    coating
    -0.33
     swat
    -0.32
    Stro
    -0.32
    POSITIVE LOGITS
    AndEndTag
    0.62
    TagMode
    0.50
     AssemblyCulture
    0.47
     normais
    0.46
    IntoConstraints
    0.46
    舺
    0.43
    FormTagHelper
    0.43
    attutto
    0.43
    digheden
    0.41
    تقاوى
    0.41
    Act Density 0.040%

    No Known Activations