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

    Neuronpedia

    INDEX
    Explanations

    sections of text that provide descriptions or explanations

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

    description or summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.84
     &___
    -0.75
     Normdatei
    -0.69
    xhttp
    -0.68
    rungsseite
    -0.67
     queſta
    -0.65
    الحياه
    -0.64
     المعيارى
    -0.63
    balleur
    -0.62
     Wikimedijinoj
    -0.61
    POSITIVE LOGITS
    description
    0.68
    Description
    0.64
     description
    0.60
     Description
    0.59
     purpose
    0.57
    summary
    0.54
    ApiOperation
    0.50
     Purpose
    0.49
    DESCRIPTION
    0.48
     DESCRIPTION
    0.47
    Act Density 0.002%

    No Known Activations