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

    Neuronpedia

    INDEX
    Explanations

    emphatic adjectives describing uniqueness or significance

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

    Preceding adverbs modifying a verb

    np_acts-logits-general · gemini-2.0-flash

    words indicating degree or scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Detox
    -0.57
     sanity
    -0.56
    rungsseite
    -0.55
     Officially
    -0.54
     مشين
    -0.54
    officially
    -0.54
     Vergrößern
    -0.54
     confis
    -0.54
     Visualization
    -0.53
    Medica
    -0.53
    POSITIVE LOGITS
     sobretudo
    0.70
     broader
    0.64
     broad
    0.57
    whelming
    0.57
     zugleich
    0.53
    broad
    0.52
     fundamentales
    0.52
     profound
    0.52
    retudo
    0.52
     substance
    0.51
    Act Density 0.370%

    No Known Activations