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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Spoiler
    -0.07
     APS
    -0.07
     Hopkins
    -0.07
     gland
    -0.06
     Cod
    -0.06
     typings
    -0.06
     فوتبال
    -0.06
    faq
    -0.06
     Bulgarian
    -0.06
    AH
    -0.06
    POSITIVE LOGITS
    esto
    0.07
    .Before
    0.07
     EXISTS
    0.07
    .output
    0.06
     nhánh
    0.06
    .uint
    0.06
     NoSuchElementException
    0.06
     slož
    0.06
     خارجية
    0.06
    ("//
    0.06
    Act Density 0.018%

    No Known Activations