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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a range of types or categories

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

    a wide variety of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.63
     EconPapers
    -0.62
    ImageContext
    -0.59
    penup
    -0.57
     jsPsych
    -0.56
    verwijspagina
    -0.56
    #+#
    -0.56
    RenderAtEndOf
    -0.54
    StoryboardSegue
    -0.54
    تقاوى
    -0.52
    POSITIVE LOGITS
    tissimi
    0.56
     ErrIntOverflow
    0.49
    Portail
    0.43
     keinerlei
    0.43
    これだけ
    0.41
    NumberOf
    0.40
    TotalCount
    0.40
     dzied
    0.39
     überall
    0.39
     kaikki
    0.38
    Act Density 0.012%

    No Known Activations