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

    Neuronpedia

    INDEX
    Explanations

    drinking and driving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    γραφ
    -0.09
     Claude
    -0.08
    Claude
    -0.08
     Nā
    -0.08
    iquement
    -0.08
     چیز
    -0.08
    ਸਤ
    -0.08
     ਚ
    -0.08
     moth
    -0.08
     séjour
    -0.08
    POSITIVE LOGITS
     القيادة
    0.10
    驾驶
    0.10
    酒
    0.09
     fatalities
    0.09
     Fahrer
    0.09
     rijdt
    0.09
     artery
    0.09
     arterial
    0.09
     alcohol
    0.09
    fahrt
    0.08
    Act Density 0.050%

    No Known Activations