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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /io
    -0.07
     brain
    -0.06
     disabled
    -0.06
     Bean
    -0.06
     tumult
    -0.06
     endured
    -0.06
    opacity
    -0.06
     Encoding
    -0.05
     WHILE
    -0.05
     blessed
    -0.05
    POSITIVE LOGITS
     bryster
    0.08
    이를
    0.07
    Information
    0.07
    {},↵
    0.07
    orgt
    0.07
    ��
    0.07
     futures
    0.07
     Einstein
    0.06
    介绍
    0.06
    수가
    0.06
    Act Density 0.202%

    No Known Activations