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

    Neuronpedia

    INDEX
    Explanations

    Equations and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    为准
    -0.07
    partner
    -0.07
    ograph
    -0.07
    lime
    -0.06
    .import
    -0.06
     arist
    -0.06
    -instance
    -0.06
    تغيير
    -0.06
    -help
    -0.06
     Telegram
    -0.06
    POSITIVE LOGITS
    !"↵↵
    0.08
    Lab
    0.07
    ,column
    0.07
     leggings
    0.07
     должна
    0.07
     Iter
    0.07
    _bb
    0.07
    EntityType
    0.06
     Sept
    0.06
    ��
    0.06
    Act Density 0.034%

    No Known Activations