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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ма
    -0.07
     Bans
    -0.07
    ots
    -0.07
    Stock
    -0.06
     certification
    -0.06
     Volvo
    -0.06
    MU
    -0.06
    439
    -0.06
     руб
    -0.06
     Accident
    -0.06
    POSITIVE LOGITS
    ΕΙ
    0.07
     Zimbabwe
    0.07
     παρ
    0.06
     přek
    0.06
    *>
    0.06
     ایران
    0.06
    ło
    0.06
     CLASS
    0.06
    FOUND
    0.06
     قطر
    0.06
    Act Density 0.038%

    No Known Activations