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

    Neuronpedia

    INDEX
    Explanations

    structure-related elements in mathematical or scientific notation

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

    after named entities or sentence fragments

    np_acts-logits-general · gemini-2.0-flash

    words from other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.68
    .
    -0.58
    in
    -0.55
    here
    -0.51
    ,
    -0.51
    AfterViewInit
    -0.50
    les
    -0.49
     (
    -0.48
    ó
    -0.48
     on
    -0.48
    POSITIVE LOGITS
    ressum
    0.91
     Anſ
    0.90
    Geplaatst
    0.89
     Савезне
    0.88
     purpoſe
    0.83
    spesies
    0.81
    ousand
    0.81
     perſon
    0.81
     ainfi
    0.80
     auffi
    0.80
    Act Density 0.311%

    No Known Activations