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

    Neuronpedia

    INDEX
    Explanations

    English language text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dakota
    -0.07
    ßerdem
    -0.06
     wo
    -0.06
    Fant
    -0.06
    Mad
    -0.06
    ramework
    -0.06
     круг
    -0.06
     jer
    -0.06
    simulation
    -0.06
     sunny
    -0.06
    POSITIVE LOGITS
     curvature
    0.08
     Федера
    0.07
     ward
    0.06
     HashMap
    0.06
     gén
    0.06
    ：%
    0.06
     GW
    0.06
    ALLENG
    0.06
    /%
    0.06
    他的
    0.06
    Act Density 0.000%

    No Known Activations