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

    Neuronpedia

    INDEX
    Explanations

    Asking about activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SSC
    -0.07
    hum
    -0.07
    ospel
    -0.06
     Mama
    -0.06
     nun
    -0.06
    ゆ
    -0.06
    istles
    -0.06
    ‌ها
    -0.06
    Travel
    -0.06
    -tone
    -0.06
    POSITIVE LOGITS
    建议
    0.07
    atitude
    0.07
    [".
    0.06
     secretive
    0.06
     dentist
    0.06
     enabling
    0.06
     sélection
    0.06
     detections
    0.06
     dynamics
    0.06
    fillna
    0.06
    Act Density 0.029%

    No Known Activations