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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to mathematical modeling and optimization methods

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

    mathematical and conditional concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➟
    -0.45
     المعيارى
    -0.39
    يميديا
    -0.35
     kerajaan
    -0.33
     Ded
    -0.33
     ujednoznacz
    -0.32
     Exacts
    -0.31
     PagesJaunes
    -0.31
    angel
    -0.30
    TRIBUN
    -0.30
    POSITIVE LOGITS
     wikipagina
    0.59
    transQ
    0.56
     myſelf
    0.52
     Bewußt
    0.51
     betweenstory
    0.51
     незавершена
    0.49
     盗撮
    0.49
    IsMutable
    0.48
     deſt
    0.48
     isSet
    0.48
    Act Density 0.599%

    No Known Activations