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

    Neuronpedia

    INDEX
    Explanations

    references to various types of halls and their attributes

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

    hall or gymnasium

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.50
    enumii
    -0.44
     protoimpl
    -0.43
    snap
    -0.42
    weet
    -0.41
     surla
    -0.40
     Snap
    -0.40
     snap
    -0.40
    PyExc
    -0.40
     Catawiki
    -0.40
    POSITIVE LOGITS
     halls
    0.96
     hall
    0.95
     salão
    0.87
     Halls
    0.86
     salle
    0.80
     HALL
    0.79
     зал
    0.78
     auditorium
    0.77
     Auditorium
    0.75
     Hall
    0.72
    Act Density 0.018%

    No Known Activations