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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Advantage
    -0.08
    Disabled
    -0.08
    (chip
    -0.07
     NDP
    -0.07
     Sacred
    -0.07
    特点
    -0.07
     Curriculum
    -0.07
    .deg
    -0.07
     varied
    -0.06
     Heritage
    -0.06
    POSITIVE LOGITS
    珊
    0.07
     עם
    0.07
    glm
    0.07
    年至
    0.07
     met
    0.07
    old
    0.07
    Constructed
    0.07
    上
    0.07
    设施建设
    0.06
     connects
    0.06
    Act Density 0.032%

    No Known Activations