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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Θ
    -0.06
    _den
    -0.06
    اعات
    -0.06
    op
    -0.06
    εται
    -0.06
     silly
    -0.06
    وش
    -0.06
     stations
    -0.06
     station
    -0.06
    اشی
    -0.06
    POSITIVE LOGITS
    -too
    0.07
    ConstraintMaker
    0.07
    .keyword
    0.07
    responseData
    0.07
     iq
    0.06
     مهند
    0.06
     ############
    0.06
     เม
    0.06
     serde
    0.06
     передбач
    0.06
    Act Density 0.001%

    No Known Activations