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

    Neuronpedia

    INDEX
    Explanations

    AE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -､
    -0.07
    StdString
    -0.07
     INST
    -0.06
     gratuiti
    -0.06
    .Intent
    -0.06
     تول
    -0.06
     Ты
    -0.06
    Endpoints
    -0.06
    larındaki
    -0.06
     він
    -0.06
    POSITIVE LOGITS
    ака
    0.08
     Kaiser
    0.08
    aq
    0.07
    Ag
    0.07
     Jake
    0.07
    AE
    0.07
    áf
    0.07
    audi
    0.07
    aji
    0.07
    ao
    0.07
    Act Density 0.211%

    No Known Activations