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

    Neuronpedia

    INDEX
    Explanations

    math and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     НА
    -0.06
    '>
↵
    -0.06
    SelfPermission
    -0.06
    इ
    -0.06
    axies
    -0.06
     Pix
    -0.06
    职
    -0.06
     dig
    -0.05
    $q
    -0.05
     sa
    -0.05
    POSITIVE LOGITS
    术
    0.06
    ِّ
    0.06
     ابت
    0.06
     método
    0.06
    @return
    0.06
     ارتفاع
    0.06
     меш
    0.06
    NGTH
    0.06
    (SK
    0.06
    _emb
    0.06
    Act Density 0.043%

    No Known Activations