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

    Neuronpedia

    INDEX
    Explanations

    references to methods and systems related to data organization and functionality

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

    "Same" or similar words appearing in different languages

    np_acts-logits-general · gemini-2.0-flash

    same thing as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.93
     Савезне
    -0.74
     дописавши
    -0.72
    GraphicsUnit
    -0.72
    __*/
    -0.69
     كومونز
    -0.69
     EconPapers
    -0.68
    VersionUID
    -0.68
    ResumeLayout
    -0.66
    EndProject
    -0.66
    POSITIVE LOGITS
     same
    0.76
    same
    0.72
    Same
    0.67
     Same
    0.66
     kuin
    0.66
     but
    0.59
     as
    0.54
    zelfde
    0.54
     aynı
    0.54
     exact
    0.54
    Act Density 0.213%

    No Known Activations