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

    Neuronpedia

    INDEX
    Explanations

    text that discusses popularity, ratings, or critical reception in various contexts

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

    preceding common follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.41
    Autoritní
    -0.36
    match
    -0.35
    Cubit
    -0.35
    BagConstraints
    -0.34
    KURZBESCHREIBUNG
    -0.34
    ויות
    -0.33
    碰
    -0.33
    measure
    -0.32
    gatsby
    -0.32
    POSITIVE LOGITS
    Tembelea
    0.62
    ItemBackground
    0.56
    BufferException
    0.56
    verwijspagina
    0.55
    MessageOf
    0.54
     EconPapers
    0.51
     penting
    0.50
    ьаж
    0.49
     gustó
    0.48
    galkan
    0.48
    Act Density 0.296%

    No Known Activations