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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate formal declarations or statements made by individuals or entities

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

    following articles ("a," "an," "our")

    np_acts-logits-general · gemini-2.0-flash

    articles followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ItemBackground
    -0.75
    aarrggbb
    -0.75
     متعلقه
    -0.74
    expandindo
    -0.73
    Vidite
    -0.61
    SharedCtor
    -0.58
    PreferredItem
    -0.57
     Trials
    -0.57
    spira
    -0.57
     kasarigan
    -0.57
    POSITIVE LOGITS
     letter
    0.89
     email
    0.69
     lengthy
    0.68
     recent
    0.66
     interview
    0.62
     lettre
    0.59
     lettera
    0.58
     handwritten
    0.57
     skrift
    0.55
     telephone
    0.55
    Act Density 0.263%

    No Known Activations