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

    Neuronpedia

    INDEX
    Explanations

    references to software updates and enhancements

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

    Software updates, improvements, and fixes

    np_acts-logits-general · gemini-2.0-flash

    software updates and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.45
     PeEnEo
    -0.43
     montagem
    -0.42
    RTGC
    -0.42
    Diweddarwch
    -0.41
     autorytatywna
    -0.40
    TagHelper
    -0.38
    ⓧ
    -0.35
     représentation
    -0.35
    knapp
    -0.34
    POSITIVE LOGITS
     updates
    0.55
     improvements
    0.51
     adjustments
    0.49
     feedback
    0.47
     revisions
    0.47
     roadmap
    0.46
     iParam
    0.46
     optimizations
    0.46
     refinements
    0.44
     createSlice
    0.44
    Act Density 0.150%

    No Known Activations