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

    Neuronpedia

    INDEX
    Explanations

    indicators of errors or failures in the code context

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

    appearing in code or code-like contexts

    np_acts-logits-general · gemini-2.0-flash

    API request fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     back
    -0.67
     comeback
    -0.67
     reappeared
    -0.65
     rejo
    -0.64
     reverted
    -0.63
     recoveries
    -0.62
     recover
    -0.61
     rejoin
    -0.61
     resur
    -0.60
     returns
    -0.60
    POSITIVE LOGITS
    IBOutlet
    0.65
    DockStyle
    0.62
     متعلقه
    0.61
     étrang
    0.61
     regulador
    0.61
     chré
    0.60
    contentLoaded
    0.60
     sauvages
    0.60
     betweenstory
    0.58
    Portail
    0.55
    Act Density 0.084%

    No Known Activations