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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and organizations in various contexts

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

    dates and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.45
     desmotivaciones
    -0.45
    isContained
    -0.42
     виправивши
    -0.40
    UseVisualStyle
    -0.39
     snippetHide
    -0.39
    onViewCreated
    -0.39
     uſed
    -0.38
    TagMode
    -0.38
     romantique
    -0.38
    POSITIVE LOGITS
     thereafter
    0.54
    finally
    0.54
     majd
    0.54
    Finalmente
    0.52
     finally
    0.52
     Finally
    0.51
    again
    0.51
    Finally
    0.50
     again
    0.48
     Finalmente
    0.48
    Act Density 0.108%

    No Known Activations