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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usuarios
    -0.07
     transit
    -0.07
    .auth
    -0.07
    ruc
    -0.07
     ع
    -0.07
    /gcc
    -0.07
     Stunden
    -0.06
     hatten
    -0.06
     versus
    -0.06
     newSize
    -0.06
    POSITIVE LOGITS
     pry
    0.08
     bait
    0.07
    旅程
    0.07
    idious
    0.07
     роли
    0.07
     objectively
    0.07
     daemon
    0.07
    就越
    0.07
    目的在于
    0.07
    产物
    0.06
    Act Density 0.002%

    No Known Activations