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

    Neuronpedia

    INDEX
    Explanations

    unread

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -col
    -0.07
     harness
    -0.07
     nét
    -0.07
    苑
    -0.07
     누
    -0.07
     aficion
    -0.07
    煨
    -0.06
    冉
    -0.06
    색
    -0.06
    残疾
    -0.06
    POSITIVE LOGITS
    #if
    0.07
    人人都
    0.06
     Happiness
    0.06
     QVERIFY
    0.06
     Nicol
    0.06
     antibody
    0.06
     dieser
    0.06
     bottleneck
    0.06
    INAL
    0.06
    哥伦比亚
    0.06
    Act Density 0.001%

    No Known Activations