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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zaměstn
    -0.07
     Brock
    -0.07
    enticated
    -0.07
     　 　
    -0.07
     Advantage
    -0.07
     "{\"
    -0.06
    -0.06
    ***/↵↵
    -0.06
    .*;↵↵
    -0.06
    Portály
    -0.06
    POSITIVE LOGITS
    朋
    0.07
     accuse
    0.07
    ileş
    0.06
    ческого
    0.06
    sense
    0.06
    guid
    0.06
     nimi
    0.06
    guide
    0.06
    -extension
    0.06
     وت
    0.06
    Act Density 0.075%

    No Known Activations