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

    Neuronpedia

    INDEX
    Explanations

    repeated underscores, indicating placeholders or formatting in text

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

    `<start_of_turn> user`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.56
     оригіналу
    -0.52
     ostavi
    -0.50
    ⸄
    -0.50
    orianCalendar
    -0.50
    etak
    -0.49
    BorderLayout
    -0.48
    ście
    -0.48
    ecap
    -0.48
    Wut
    -0.48
    POSITIVE LOGITS
     table
    0.40
     casada
    0.35
    SharedCtor
    0.35
     informée
    0.33
    WithIOException
    0.30
     &___
    0.30
     Substanz
    0.30
    glDelete
    0.30
     pravidel
    0.29
    glClear
    0.29
    Act Density 0.001%

    No Known Activations