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

    Neuronpedia

    INDEX
    Explanations

    specific noun phrases related to locations and scenarios

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

    Nouns followed by prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    events and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nôtre
    -0.70
     portions
    -0.70
    skosten
    -0.69
     batches
    -0.68
     chapters
    -0.67
     pieces
    -0.67
     knots
    -0.66
     episodes
    -0.64
     symbols
    -0.63
     rectangles
    -0.63
    POSITIVE LOGITS
     situation
    0.70
     that
    0.69
     system
    0.67
     session
    0.65
     program
    0.64
     scheme
    0.64
     épaules
    0.63
    exitRule
    0.62
     scenario
    0.61
     regimen
    0.59
    Act Density 1.690%

    No Known Activations