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

    Neuronpedia

    INDEX
    Explanations

    punctuation or formatting marks in the text

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

    separators and legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deixa
    -0.26
    //
    -0.25
     incó
    -0.25
    签
    -0.23
    auer
    -0.22
     переста
    -0.21
     directores
    -0.21
     BrowserModule
    -0.21
    ➟
    -0.21
    ilanth
    -0.20
    POSITIVE LOGITS
     disambiguazione
    0.66
     ***
    0.66
     @@
    0.60
     ***/
    0.60
     CURIAM
    0.60
     '**
    0.60
     autorytatywna
    0.59
     Glance
    0.59
    +#+#
    0.58
    __((
    0.58
    Act Density 0.043%

    No Known Activations