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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quantities and measurements

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

    time after seen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poveznice
    -0.60
    ypeł
    -0.57
     transición
    -0.56
    awtextra
    -0.55
    filepath
    -0.54
     commerciaux
    -0.53
     ilustracja
    -0.52
     creatividad
    -0.51
     caminhada
    -0.51
    tvguidetime
    -0.50
    POSITIVE LOGITS
    Билгалдахарш
    0.47
     disambiguazione
    0.44
     phal
    0.42
    Xna
    0.41
    RenderAtEndOf
    0.40
     ujednoznacz
    0.40
    +#+#
    0.39
    Hochspringen
    0.39
     saltwater
    0.37
     bad
    0.35
    Act Density 0.068%

    No Known Activations