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

    Neuronpedia

    INDEX
    Explanations

    sure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chiếm
    -0.07
    ái
    -0.07
    既
    -0.06
    -0.06
     theater
    -0.06
     eaten
    -0.06
     Wiki
    -0.06
     enactment
    -0.06
    ích
    -0.06
     Eaton
    -0.06
    POSITIVE LOGITS
     sure
    0.13
     Sure
    0.08
    Sure
    0.08
    -unstyled
    0.07
    sure
    0.07
     مستقیم
    0.07
     haircut
    0.07
    mul
    0.07
     clear
    0.07
     hamburg
    0.07
    Act Density 0.019%

    No Known Activations