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

    Neuronpedia

    INDEX
    Explanations

    software licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -quality
    -0.07
     Alzheimer
    -0.06
    xia
    -0.06
     ure
    -0.06
    ık
    -0.06
     Lyme
    -0.06
    iverse
    -0.06
    高血压
    -0.06
     bacteria
    -0.06
    规划
    -0.06
    POSITIVE LOGITS
     generado
    0.07
    Г
    0.07
    (strings
    0.07
    '\
    0.07
    に対
    0.07
     unsuccessful
    0.07
    cq
    0.07
     closeModal
    0.07
     proceeded
    0.07
    삐
    0.06
    Act Density 0.028%

    No Known Activations