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

    Neuronpedia

    INDEX
    Explanations

    nature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Procedures
    -0.07
     Flower
    -0.07
    genes
    -0.07
    ер
    -0.07
    سان
    -0.06
    sticks
    -0.06
    entina
    -0.06
    ogie
    -0.06
    ]+)/
    -0.06
    abe
    -0.06
    POSITIVE LOGITS
    .retry
    0.08
    -->
↵
    0.07
    -main
    0.07
    ازی
    0.07
    ]',↵
    0.06
     üz
    0.06
     अज
    0.06
    !↵↵↵↵
    0.06
    ляд
    0.06
     {?}
    0.06
    Act Density 0.008%

    No Known Activations