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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     \%
    -0.07
     Addresses
    -0.07
      ↵
    -0.06
    사지
    -0.06
    έρα
    -0.06
    037
    -0.06
    GOP
    -0.06
     kitty
    -0.06
     краще
    -0.06
    MLE
    -0.06
    POSITIVE LOGITS
    /history
    0.08
    Ticker
    0.07
    ски
    0.06
     crackdown
    0.06
    ursion
    0.06
     selbst
    0.06
     unchanged
    0.06
    、中
    0.06
     bomber
    0.06
    οντας
    0.06
    Act Density 0.197%

    No Known Activations