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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /categories
    -0.08
    ustria
    -0.08
     quienes
    -0.07
    庐
    -0.07
    ᐈ
    -0.07
    .sig
    -0.07
    اليابان
    -0.07
    由此可见
    -0.07
    سعادة
    -0.07
    されること
    -0.07
    POSITIVE LOGITS
     Rate
    0.07
     One
    0.07
     gele
    0.07
     dbo
    0.07
    Ah
    0.07
    pper
    0.07
     Marshal
    0.07
     HomeController
    0.06
     recorded
    0.06
    pose
    0.06
    Act Density 0.006%

    No Known Activations