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

    Neuronpedia

    INDEX
    Explanations

    references to tags and their associated actions or properties

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

    tags and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.61
    __":
    -0.57
    новништво
    -0.56
    enterOuterAlt
    -0.55
     يتيمه
    -0.54
    __':
    -0.53
     disambiguazione
    -0.51
     utafitiHapana
    -0.51
     <>",
    -0.51
    MLLoader
    -0.50
    POSITIVE LOGITS
     tags
    0.58
    tags
    0.52
     Wiktionnaire
    0.47
    Tags
    0.45
     Tags
    0.44
     keywords
    0.42
    TAGS
    0.42
     hashtags
    0.40
     tag
    0.39
     keyword
    0.37
    Act Density 0.031%

    No Known Activations