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

    Neuronpedia

    INDEX
    Explanations

    references to buildings and their structural features, particularly windows and doors

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

    windows or doors

    np_acts-logits-general · gemini-2.0-flash

    windows and doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnknownFieldSet
    -0.75
     EconPapers
    -0.65
    RegistryLite
    -0.63
    EndInit
    -0.62
     ويكيپيديا
    -0.61
    kháu
    -0.61
     autorytatywna
    -0.59
    ViewFeatures
    -0.59
    tagext
    -0.59
     CreateTagHelper
    -0.59
    POSITIVE LOGITS
     sash
    0.72
     windows
    0.69
     oper
    0.64
    Case
    0.62
     case
    0.60
    operable
    0.58
     sas
    0.58
     Case
    0.57
     double
    0.57
     triple
    0.56
    Act Density 0.077%

    No Known Activations