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

    Neuronpedia

    INDEX
    Explanations

    below

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     course
    -0.07
     dětí
    -0.07
     sugars
    -0.06
     picking
    -0.06
    UnderTest
    -0.06
     Courses
    -0.06
    цией
    -0.06
    arsed
    -0.06
    ного
    -0.06
     intensive
    -0.06
    POSITIVE LOGITS
    Below
    0.07
     Below
    0.07
     PSU
    0.07
     chó
    0.07
     <?=$
    0.07
     Mattis
    0.07
    -shell
    0.06
    _BTN
    0.06
     Київ
    0.06
    	arr
    0.06
    Act Density 0.004%

    No Known Activations