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

    Neuronpedia

    INDEX
    Explanations

    words that indicate something being reported or said

    oai_token-act-pair · gemini-2.0-flash

    "as" in many languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.84
    thenia
    -0.75
    ChildScrollView
    -0.75
    PreferredItem
    -0.75
    脚注の使い方
    -0.73
     lenker
    -0.70
     disambiguazione
    -0.69
     Theſe
    -0.68
     الحره
    -0.68
    tvguidetime
    -0.67
    POSITIVE LOGITS
     as
    2.69
     sebagai
    1.40
    as
    1.32
     как
    1.21
    作为
    1.13
    作為
    1.08
     као
    0.98
     як
    0.96
     jako
    0.95
     ως
    0.94
    Act Density 2.110%

    No Known Activations