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

    Neuronpedia

    INDEX
    Explanations

    terms related to data evaluation and comparison methods

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

    using methods or integration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.53
     debout
    -0.49
     disambiguazione
    -0.48
     faſt
    -0.48
     itſelf
    -0.47
    mous
    -0.45
     pleaſure
    -0.45
     houſe
    -0.44
    AutoresizingMask
    -0.44
     themſelves
    -0.43
    POSITIVE LOGITS
     improved
    0.53
     methods
    0.47
     improvements
    0.46
     Absch
    0.45
     overlook
    0.44
     procedure
    0.44
     Improved
    0.44
     using
    0.44
     amelior
    0.44
     Baer
    0.43
    Act Density 0.282%

    No Known Activations