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

    Neuronpedia

    INDEX
    Explanations

    grade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ekl
    -0.07
    Tour
    -0.06
     Presence
    -0.06
    Summary
    -0.06
    ※
    -0.06
    jure
    -0.06
    ias
    -0.06
    Hu
    -0.06
     преж
    -0.06
    美國
    -0.06
    POSITIVE LOGITS
     فهم
    0.07
    .Full
    0.07
    (pid
    0.06
    -view
    0.06
     lối
    0.06
     personn
    0.06
    (has
    0.06
     dat
    0.06
     UserProfile
    0.06
     نگ
    0.06
    Act Density 0.024%

    No Known Activations