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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Santiago
    -0.07
     Venom
    -0.07
    MEMORY
    -0.06
    _UI
    -0.06
    chop
    -0.06
     Tunnel
    -0.06
    .restaurant
    -0.06
     روز
    -0.06
     Hue
    -0.06
     یون
    -0.06
    POSITIVE LOGITS
    .group
    0.06
     posters
    0.06
     ягод
    0.06
    εται
    0.06
     errores
    0.06
    .setAuto
    0.06
     пот
    0.06
    عة
    0.06
    안
    0.06
    etail
    0.05
    Act Density 0.057%

    No Known Activations