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

    Neuronpedia

    INDEX
    Explanations

    df

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Allocator
    -0.08
    _DYNAMIC
    -0.08
    不见
    -0.07
    Episode
    -0.07
     Wander
    -0.07
    襚
    -0.07
     meine
    -0.07
     Swarm
    -0.07
    describe
    -0.07
     essay
    -0.06
    POSITIVE LOGITS
     />\
    0.07
    خف
    0.07
    ત
    0.07
    推广
    0.07
    目前
    0.07
     cộng
    0.06
    .tm
    0.06
    _u
    0.06
    quared
    0.06
     FactoryBot
    0.06
    Act Density 0.001%

    No Known Activations