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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    steller
    -0.07
    нувся
    -0.07
     غرب
    -0.07
     RDD
    -0.07
    RDD
    -0.07
    FO
    -0.06
     overall
    -0.06
    pendicular
    -0.06
    ційна
    -0.06
     spheres
    -0.06
    POSITIVE LOGITS
     Wie
    0.07
     Kee
    0.06
     pdo
    0.06
     Priv
    0.06
     tie
    0.06
    ()._
    0.06
     flakes
    0.06
    (te
    0.06
    (mut
    0.06
     Guam
    0.06
    Act Density 0.000%

    No Known Activations