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

    Neuronpedia

    INDEX
    Explanations

    professions unions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orientation
    -0.08
     orientations
    -0.07
     safe
    -0.07
     يا
    -0.06
    48
    -0.06
     Owl
    -0.06
    ۲۴
    -0.06
    ké
    -0.06
     управления
    -0.06
     cur
    -0.06
    POSITIVE LOGITS
    [`
    0.07
    [".
    0.06
     Garcia
    0.06
    unft
    0.06
    _class
    0.06
    λης
    0.06
    HDATA
    0.06
    .TestTools
    0.06
    owell
    0.06
    =${
    0.06
    Act Density 0.054%

    No Known Activations