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

    Neuronpedia

    INDEX
    Explanations

    numerical data and special symbols

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

    Non-English text and symbols

    np_acts-logits-general · gemini-2.0-flash

    sequences containing specific letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -1.15
     Wikimedijinoj
    -1.10
     resourceCulture
    -1.08
     BRARY
    -1.08
     ProtoMessage
    -1.06
    InjectAttribute
    -1.06
    ſelves
    -1.06
    Datuak
    -1.05
    setVerticalGroup
    -1.04
    EndGlobalSection
    -1.04
    POSITIVE LOGITS
    .
    0.80
    ,
    0.74
    ?
    0.72
     I
    0.72
    ↵
    0.68
    !
    0.68
     C
    0.67
    I
    0.66
    ;
    0.64
     E
    0.64
    Act Density 0.549%

    No Known Activations