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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authorship and founding roles

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

    author of works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PullParser
    -0.41
     Extragalactic
    -0.40
     Personne
    -0.40
    цездатний
    -0.39
     Neigh
    -0.38
    People
    -0.36
    Resident
    -0.36
    intios
    -0.36
     UTM
    -0.36
    Personne
    -0.36
    POSITIVE LOGITS
    author
    0.71
     authored
    0.68
     author
    0.66
     Author
    0.58
    Authors
    0.57
     authors
    0.57
    StoryboardSegue
    0.57
     autor
    0.57
    autor
    0.56
     autora
    0.56
    Act Density 0.018%

    No Known Activations