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

    Neuronpedia

    INDEX
    Explanations

    names and proper nouns related to events or individuals

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

    ending in common suffixes

    np_acts-logits-general · gemini-2.0-flash

    names in citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.45
    XmlAccessType
    -0.36
     Re
    -0.33
     Ne
    -0.32
     Bu
    -0.32
     si
    -0.31
    kháu
    -0.31
    readAs
    -0.31
    黄
    -0.30
     فض
    -0.30
    POSITIVE LOGITS
     ModelExpression
    0.64
    abestanden
    0.64
    DeleteBehavior
    0.60
    ToBounds
    0.57
    ſammen
    0.57
     Wikimedijinoj
    0.56
     CreateTagHelper
    0.56
    ⪜
    0.55
    bewerken
    0.55
     CURIAM
    0.54
    Act Density 1.243%

    No Known Activations