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

    Neuronpedia

    INDEX
    Explanations

    "на всякий случай"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     达
    -0.08
    cule
    -0.08
    ponsor
    -0.08
     WW
    -0.07
     curto
    -0.07
    Excellent
    -0.07
     Kona
    -0.07
     intéressant
    -0.07
     vigtig
    -0.07
     leisten
    -0.07
    POSITIVE LOGITS
     precaution
    0.12
     unsure
    0.10
     возмож
    0.10
     precautions
    0.09
    万
    0.09
     dubbel
    0.08
     possibile
    0.08
     cautiously
    0.08
     сом
    0.08
     Poland
    0.08
    Act Density 0.006%

    No Known Activations