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

    Neuronpedia

    INDEX
    Explanations

    legal rulings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suction
    -0.07
     Mistress
    -0.07
     Histogram
    -0.06
    Tester
    -0.06
     steer
    -0.06
     debris
    -0.06
    middlewares
    -0.06
     FR
    -0.06
     philosophy
    -0.06
     bracelet
    -0.06
    POSITIVE LOGITS
     smo
    0.07
     έχει
    0.07
     jsem
    0.06
     Ens
    0.06
     crea
    0.06
    Health
    0.06
    Being
    0.06
    orta
    0.06
     Sous
    0.06
     nạn
    0.06
    Act Density 0.034%

    No Known Activations