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

    Neuronpedia

    INDEX
    Explanations

    statements about uncertainty and subjectivity in clinical observations or research findings

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

    instances of the word "is" and other phrases denoting importance or significance

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

    is followed by a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    colour
    -0.67
    coloured
    -0.64
     flavour
    -0.64
     colouring
    -0.61
    haviour
    -0.59
    Colour
    -0.59
     Honour
    -0.58
    Favourite
    -0.58
    colours
    -0.58
     honour
    -0.57
    POSITIVE LOGITS
    IsContent
    0.71
    MultipartFile
    0.61
    ROIT
    0.59
    TextBoxColumn
    0.56
     članak
    0.55
     theater
    0.55
     BoxFit
    0.54
     fiber
    0.54
    OrNil
    0.53
    AndEndTag
    0.53
    Act Density 0.074%

    No Known Activations