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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disdain
    -0.07
     highways
    -0.07
     à
    -0.07
    zet
    -0.06
     smile
    -0.06
     friendship
    -0.06
    getPath
    -0.06
    يق
    -0.06
     pueblo
    -0.06
     tears
    -0.06
    POSITIVE LOGITS
    ipheral
    0.07
    Previous
    0.07
     ชนะ
    0.07
    ifferent
    0.07
    -dimensional
    0.07
     речов
    0.07
    是什么
    0.06
    ÜR
    0.06
     ROS
    0.06
    ?>/
    0.06
    Act Density 0.000%

    No Known Activations