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

    Neuronpedia

    INDEX
    Explanations

    phrases that express agreement or shared feelings about significant concepts

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

    to me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.51
     Grüsse
    -0.42
     يتيمه
    -0.40
    NameInMap
    -0.40
     autorytatywna
    -0.40
    RenderAtEndOf
    -0.39
    Geografía
    -0.38
    PerformLayout
    -0.38
     bailarina
    -0.38
    Autoritní
    -0.37
    POSITIVE LOGITS
    gapa
    0.45
     препратки
    0.44
    향
    0.43
     Arn
    0.41
    onio
    0.41
     aberration
    0.41
     onOptions
    0.41
    ossa
    0.41
    TagMode
    0.41
     Aus
    0.40
    Act Density 0.038%

    No Known Activations