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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .TextBox
    -0.07
     orc
    -0.07
     activates
    -0.06
     Yellow
    -0.06
    "value
    -0.06
    握
    -0.06
     "$
    -0.06
    蛋
    -0.06
    -cross
    -0.06
    考试
    -0.06
    POSITIVE LOGITS
    672
    0.07
    리가
    0.07
     IPT
    0.06
    ercul
    0.06
    mAh
    0.06
    _Report
    0.06
    765
    0.06
    ycles
    0.06
     Archer
    0.06
     Rim
    0.06
    Act Density 0.000%

    No Known Activations