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

    Neuronpedia

    INDEX
    Explanations

    Future decisions and effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     黄
    -0.07
     maintenant
    -0.07
    .FirebaseAuth
    -0.06
     Percy
    -0.06
     balık
    -0.06
     Phạm
    -0.06
     chạy
    -0.06
     ajud
    -0.06
    ince
    -0.06
     просто
    -0.06
    POSITIVE LOGITS
     Adaptive
    0.07
     PIO
    0.06
     congest
    0.06
    Land
    0.06
     resistor
    0.06
     pore
    0.06
    -strokes
    0.06
     Bram
    0.06
    HomeAs
    0.06
    _PASSWORD
    0.06
    Act Density 0.205%

    No Known Activations