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

    Neuronpedia

    INDEX
    Explanations

    references to legal or regulatory actions and their implications

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

    actions taken or extent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    JSONException
    -0.36
     Bren
    -0.35
     merak
    -0.33
     sunlight
    -0.32
     old
    -0.32
     Old
    -0.30
     учитель
    -0.30
    Redraw
    -0.29
    łac
    -0.29
    setBold
    -0.29
    POSITIVE LOGITS
     Maßnahmen
    0.81
    措施
    0.79
     الحره
    0.78
    regelen
    0.78
    measures
    0.78
     kasarigan
    0.77
     provved
    0.75
     misure
    0.70
     Measures
    0.70
    Measures
    0.70
    Act Density 0.081%

    No Known Activations