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

    Neuronpedia

    INDEX
    Explanations

    error messages and related coding terms

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

    error codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.40
     дописавши
    -0.40
    utiny
    -0.36
    μερα
    -0.35
    TextHelper
    -0.33
     &___
    -0.32
    felizmente
    -0.31
    webElementXpaths
    -0.31
     ***!
    -0.30
    DeleteBehavior
    -0.29
    POSITIVE LOGITS
     insufficient
    1.15
     too
    1.05
     missing
    0.95
     inadequate
    0.95
     Too
    0.91
    too
    0.88
     wrong
    0.88
     Insufficient
    0.87
     lack
    0.87
     excessive
    0.86
    Act Density 0.110%

    No Known Activations