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

    Neuronpedia

    INDEX
    Explanations

    characteristics and classifications related to objects, including their dimensions, types, and variations

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

    kinds, types, groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intStringLen
    -0.58
    AddTagHelper
    -0.44
    tonode
    -0.43
    GoogleApiClient
    -0.41
     pulumi
    -0.41
     للاسماء
    -0.40
    Yee
    -0.40
    civi
    -0.40
    OfWork
    -0.38
     Amen
    -0.37
    POSITIVE LOGITS
     ayudarte
    0.40
    sizeCache
    0.40
     kaynağından
    0.40
    ajte
    0.40
    esterno
    0.39
    BibitemShut
    0.39
    とも言
    0.38
    Regardless
    0.38
    Sometimes
    0.38
    atores
    0.37
    Act Density 0.152%

    No Known Activations