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

    Neuronpedia

    INDEX
    Explanations

    Status

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    دری
    -0.07
    転
    -0.07
    ött
    -0.07
    lín
    -0.07
    antor
    -0.06
     ăn
    -0.06
    gem
    -0.06
     багатьох
    -0.06
     Aur
    -0.06
     heiß
    -0.06
    POSITIVE LOGITS
     immune
    0.08
    058
    0.07
     Wellness
    0.07
     daunting
    0.06
     optics
    0.06
    desk
    0.06
     educators
    0.06
     dinh
    0.06
     whatsoever
    0.06
     GLuint
    0.06
    Act Density 0.000%

    No Known Activations