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

    Neuronpedia

    INDEX
    Explanations

    specific structural or organizational elements in text

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

    first-line anti

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ioutil
    -0.38
    chränk
    -0.36
    ktı
    -0.35
     sınır
    -0.34
     oubli
    -0.34
     battre
    -0.34
     soñ
    -0.33
     prazo
    -0.33
    jnych
    -0.32
     olmuş
    -0.31
    POSITIVE LOGITS
    RegressionTest
    0.61
    msgTypes
    0.59
     linkovi
    0.57
    thâu
    0.55
     ffilmiau
    0.55
     estekak
    0.54
    LookAnd
    0.53
     PeEnEo
    0.52
    تقاوى
    0.50
    richTextPanel
    0.50
    Act Density 0.000%

    No Known Activations