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

    Neuronpedia

    INDEX
    Explanations

    the presence of a document's beginning or introduction markers

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

    Appears before uncommon words/tokens

    np_acts-logits-general · gemini-2.0-flash

    months until

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     весьма
    -0.69
    Perhaps
    -0.68
    perhaps
    -0.68
     perhaps
    -0.64
     jenen
    -0.62
    (!)
    -0.61
    eraard
    -0.60
     Perhaps
    -0.59
     jenem
    -0.59
     "...
    -0.59
    POSITIVE LOGITS
     Cancelled
    0.65
     Quora
    0.65
     narcissist
    0.63
    Rüyada
    0.62
    setupUi
    0.61
     GREY
    0.61
    StoryboardSegue
    0.61
     Mongols
    0.61
    adomo
    0.58
    afficheront
    0.58
    Act Density 0.291%

    No Known Activations