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

    Neuronpedia

    INDEX
    Explanations

    ony

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (argv
    -0.06
     فیلم
    -0.06
     Arbeit
    -0.06
     děl
    -0.06
     Apartment
    -0.06
     seria
    -0.06
     tekrar
    -0.06
    <Scalar
    -0.06
    ****************************************************************************
    -0.06
     अलग
    -0.06
    POSITIVE LOGITS
     Mt
    0.07
     �
    0.07
     mo
    0.06
     �
    0.06
    INA
    0.06
    -os
    0.06
    حدة
    0.06
     otur
    0.06
     Gur
    0.06
     쿠
    0.06
    Act Density 0.001%

    No Known Activations