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

    Neuronpedia

    INDEX
    Explanations

    Roman emperors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     colder
    -0.07
    (Menu
    -0.06
     turbulent
    -0.06
     rocked
    -0.06
     surrounded
    -0.06
    (stage
    -0.06
    海外
    -0.06
    .filtered
    -0.06
    してる
    -0.06
     перег
    -0.06
    POSITIVE LOGITS
     ged
    0.07
    asking
    0.07
    仿
    0.07
    build
    0.06
     بحث
    0.06
    hea
    0.06
     капит
    0.06
    .setScale
    0.06
     نشر
    0.06
    \:
    0.06
    Act Density 0.004%

    No Known Activations