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

    Neuronpedia

    INDEX
    Explanations

    ura

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    12
    -0.08
     Ten
    -0.07
     meals
    -0.07
     Dahl
    -0.07
     loaf
    -0.06
    Calling
    -0.06
     pint
    -0.06
     geile
    -0.06
     wandering
    -0.06
    Alloc
    -0.06
    POSITIVE LOGITS
     بوده
    0.07
     siguiente
    0.07
     TMPro
    0.06
     siguientes
    0.06
     následující
    0.06
     Morph
    0.06
     following
    0.06
     شناس
    0.06
     наступ
    0.06
    oom
    0.06
    Act Density 0.034%

    No Known Activations