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

    Neuronpedia

    INDEX
    Explanations

    Operating system discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atty
    -0.07
     icons
    -0.07
     belirli
    -0.06
     started
    -0.06
     üç
    -0.06
     drinks
    -0.06
     neighbours
    -0.06
    rends
    -0.06
     martin
    -0.06
     القرآن
    -0.06
    POSITIVE LOGITS
    .ShouldBe
    0.07
     Pist
    0.06
     '@/
    0.06
     ("<
    0.06
    uição
    0.06
    (&$
    0.06
    ุทธ
    0.06
    .CONT
    0.06
    �
    0.06
     quảng
    0.06
    Act Density 0.147%

    No Known Activations