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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Роз
    -0.07
     Cynthia
    -0.06
     au
    -0.06
     fier
    -0.06
    ;">↵
    -0.06
    searchModel
    -0.06
     vouchers
    -0.06
    ynthia
    -0.06
     зни
    -0.06
     행복
    -0.06
    POSITIVE LOGITS
    ذار
    0.07
     \'
    0.07
     déf
    0.07
    0.06
    ,-
    0.06
    做
    0.06
    oğ
    0.06
    -chain
    0.06
     TOTAL
    0.06
    攝
    0.06
    Act Density 0.024%

    No Known Activations