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

    Neuronpedia

    INDEX
    Explanations

    Mathematical problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dax
    -0.08
    祥
    -0.07
    明显
    -0.07
     appreci
    -0.07
     transparente
    -0.07
     uri
    -0.07
     wakhe
    -0.07
     deductible
    -0.07
    ೆಯಿಂದ
    -0.07
     absoluta
    -0.07
    POSITIVE LOGITS
     famed
    0.12
     famously
    0.11
     renowned
    0.11
     literature
    0.10
     famous
    0.10
     seminal
    0.09
     textbooks
    0.09
     textbook
    0.09
     प्रसिद्ध
    0.09
    -known
    0.09
    Act Density 0.043%

    No Known Activations