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

    Neuronpedia

    INDEX
    Explanations

    complex comparisons and analogies involving systems and structures

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

    Follows nouns

    np_acts-logits-general · gemini-2.0-flash

    sports, entertainment, or vehicles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.95
     kasarigan
    -0.82
     AssemblyTitle
    -0.78
    +#+#
    -0.78
     متعلقه
    -0.76
    enderror
    -0.75
     spéciaux
    -0.74
     propOrder
    -0.71
    ValueGeneration
    -0.71
    <?
    -0.71
    POSITIVE LOGITS
     automobile
    0.71
     golf
    0.67
     sports
    0.67
     baseball
    0.65
     car
    0.64
     toilet
    0.64
     airplane
    0.64
     movie
    0.61
     football
    0.60
     grocery
    0.60
    Act Density 0.717%

    No Known Activations