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

    Neuronpedia

    INDEX
    Explanations

    list separator

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    改进
    -0.07
     frequency
    -0.07
    seq
    -0.07
     winter
    -0.07
    .measure
    -0.07
    四
    -0.06
    实
    -0.06
    Read
    -0.06
    这个
    -0.06
    משכ
    -0.06
    POSITIVE LOGITS
     sout
    0.07
     pleasure
    0.07
     URLs
    0.07
    领袖
    0.07
    odom
    0.07
    BuilderInterface
    0.07
    _ads
    0.07
    🖑
    0.07
    &nbsp
    0.06
    parentNode
    0.06
    Act Density 0.072%

    No Known Activations