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

    Neuronpedia

    INDEX
    Explanations

    collections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kneeling
    -0.07
     Mood
    -0.07
     bottoms
    -0.07
     Rams
    -0.07
     BOTTOM
    -0.07
    average
    -0.07
    -shaped
    -0.07
    Florida
    -0.07
     unlawful
    -0.06
     projector
    -0.06
    POSITIVE LOGITS
    (grammar
    0.07
    };
    0.07
    .datab
    0.06
     доз
    0.06
     siyas
    0.06
     kiệm
    0.06
     �
    0.06
    [sizeof
    0.06
     завд
    0.06
     작
    0.06
    Act Density 0.046%

    No Known Activations