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

    Neuronpedia

    INDEX
    Explanations

    sections of text that contain general information or references to various categories and topics

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

    general information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.64
    fromnode
    -0.60
    tagHelperRunner
    -0.60
    
    -0.60
    Tikang
    -0.59
    HasIndex
    -0.59
    Diwedd
    -0.59
     Wikimedijinoj
    -0.58
    tonode
    -0.57
    AddTagHelper
    -0.54
    POSITIVE LOGITS
    GENERAL
    0.67
    General
    0.66
     general
    0.64
     generales
    0.62
    general
    0.60
     General
    0.59
     GENERAL
    0.59
    eneral
    0.50
     algemene
    0.48
    gemeen
    0.48
    Act Density 0.015%

    No Known Activations