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

    Neuronpedia

    INDEX
    Explanations

    Little Red Riding Hood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swell
    -0.08
     consortium
    -0.08
    cią
    -0.08
     terap
    -0.08
    -ground
    -0.08
    -focus
    -0.07
     platinum
    -0.07
     amph
    -0.07
     көб
    -0.07
    观
    -0.07
    POSITIVE LOGITS
     Bakery
    0.08
     Lidl
    0.08
     worried
    0.08
     Dairy
    0.08
     ഭക്ഷ
    0.08
     вред
    0.08
     confused
    0.07
     boissons
    0.07
     betrayed
    0.07
     '@/
    0.07
    Act Density 0.002%

    No Known Activations