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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bea
    -0.07
    [".
    -0.07
     Fond
    -0.07
     �
    -0.06
     Bee
    -0.06
     ";
    -0.06
     legislative
    -0.06
    牧
    -0.06
    .userInteractionEnabled
    -0.06
    Can
    -0.06
    POSITIVE LOGITS
     treffen
    0.07
     Misc
    0.07
    imshow
    0.07
     números
    0.06
    उन
    0.06
    หมด
    0.06
    したら
    0.06
    storybook
    0.06
     asign
    0.06
    sembled
    0.06
    Act Density 0.067%

    No Known Activations