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

    Neuronpedia

    INDEX
    Explanations

    Category

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wolves
    -0.07
    یم
    -0.07
    緊
    -0.06
    .BO
    -0.06
    /engine
    -0.06
     Бер
    -0.06
    يم
    -0.06
     Roses
    -0.06
    .unique
    -0.06
    ят
    -0.06
    POSITIVE LOGITS
     Curry
    0.07
     Clifford
    0.07
    hover
    0.07
    .getInfo
    0.06
    activo
    0.06
     جی
    0.06
    running
    0.06
    uevo
    0.06
    Movement
    0.06
    arena
    0.06
    Act Density 0.009%

    No Known Activations