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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    反思
    -0.07
    _NR
    -0.07
     meals
    -0.07
     ál
    -0.07
    .GetFiles
    -0.07
    Ū
    -0.07
    solete
    -0.06
    APS
    -0.06
     tả
    -0.06
     Sadly
    -0.06
    POSITIVE LOGITS
    家庭
    0.07
     pouvez
    0.07
    埃
    0.07
    						↵
    0.07
     exert
    0.07
    >')↵
    0.07
     generally
    0.07
    均可
    0.06
    人力
    0.06
     ".$_
    0.06
    Act Density 0.000%

    No Known Activations