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

    Neuronpedia

    INDEX
    Explanations

    the word "connection" and legal terms

    oai_token-act-pair · gemini-2.0-flash

    connection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     a
    -0.57
     but
    -0.57
     he
    -0.48
     and
    -0.45
     cost
    -0.44
     so
    -0.44
     all
    -0.44
     an
    -0.44
     quit
    -0.43
     hurt
    -0.40
    POSITIVE LOGITS
     autorytatywna
    1.10
     كومونز
    1.08
    脚注の使い方
    1.05
    IndentedString
    1.04
     חיצוניים
    0.94
    setVerticalGroup
    0.92
    XmlAccessorType
    0.90
    IUrlHelper
    0.88
    KommentareTeilen
    0.88
    GraphicsUnit
    0.88
    Act Density 0.636%

    No Known Activations