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

    Neuronpedia

    INDEX
    Explanations

    Colon punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.71
    DockStyle
    -0.58
     quota
    -0.53
     Limit
    -0.53
    stall
    -0.52
     jScrollPane
    -0.49
    endpush
    -0.48
     Shack
    -0.48
    urlpatterns
    -0.48
    abb
    -0.48
    POSITIVE LOGITS
    findpost
    0.57
     disambiguazione
    0.56
    !*\
    0.54
     désert
    0.50
     osv
    0.48
    Véxase
    0.47
    uvo
    0.47
    RectangleBorder
    0.46
    ardians
    0.44
     oike
    0.44
    Act Density 0.001%

    No Known Activations