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

    Neuronpedia

    INDEX
    Explanations

    General text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (timestamp
    -0.08
    ายน
    -0.07
     фотограф
    -0.07
    icky
    -0.07
    卧
    -0.06
    ughters
    -0.06
    ⇣
    -0.06
    哥伦比亚
    -0.06
    expr
    -0.06
     vend
    -0.06
    POSITIVE LOGITS
     ""));↵
    0.07
    tz
    0.07
    )))));
↵
    0.06
     oczy
    0.06
    殃
    0.06
     WTO
    0.06
     فأ
    0.06
    -na
    0.06
    .Acc
    0.06
     squat
    0.06
    Act Density 0.249%

    No Known Activations