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

    Neuronpedia

    INDEX
    Explanations

    terms related to extremes or superiority

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

    Follows "extreme"

    np_acts-logits-general · gemini-2.0-flash

    extreme and supreme qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urlpatterns
    -0.69
     cellpadding
    -0.56
    MatButtonModule
    -0.54
     espagnole
    -0.53
     chương
    -0.53
     warts
    -0.52
    DJANGO
    -0.51
     Filosof
    -0.50
    település
    -0.50
     الشمس
    -0.49
    POSITIVE LOGITS
    MigrationBuilder
    0.83
     limits
    0.63
    actionMode
    0.59
     Limits
    0.59
     Rè
    0.57
     ekst
    0.56
    DeleteBehavior
    0.55
     ELSE
    0.55
    󠁴
    0.55
     rem
    0.55
    Act Density 0.137%

    No Known Activations