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

    Neuronpedia

    INDEX
    Explanations

    sentences that describe people

    oai_token-act-pair · gemini-2.0-flash

    technical terms or keywords

    np_token-act-pair-logits · gpt-4o-mini

    Forum/political discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     their
    -1.00
    Their
    -0.91
    their
    -0.86
     Their
    -0.85
     leur
    -0.75
     kanilang
    -0.71
    他们的
    -0.65
     leurs
    -0.63
     deres
    -0.62
     ihres
    -0.58
    POSITIVE LOGITS
    Personendaten
    1.10
    TagMode
    1.09
     nahilalakip
    1.06
     CreateTagHelper
    1.03
    CloseOperation
    1.02
    Autoritní
    0.97
    EndProject
    0.96
     '{@
    0.95
    sizeCache
    0.92
    EndGlobalSection
    0.92
    Act Density 1.699%

    No Known Activations