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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     centrales
    -0.09
     defendants
    -0.08
     proxim
    -0.08
     Redistributions
    -0.08
    逼
    -0.08
     yard
    -0.08
     squeeze
    -0.08
     incarceration
    -0.08
     sildenafil
    -0.08
     obscene
    -0.08
    POSITIVE LOGITS
     Pokémon
    0.12
     Rune
    0.09
     Vulkan
    0.09
     플레이
    0.09
     فتاة
    0.09
     Skyrim
    0.09
    攻略
    0.08
     bpy
    0.08
     villagers
    0.08
     Keeper
    0.08
    Act Density 0.012%

    No Known Activations