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

    Neuronpedia

    INDEX
    Explanations

    Buffett

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ████
    -0.07
     martyr
    -0.07
     relics
    -0.06
     abol
    -0.06
     DACA
    -0.06
     dns
    -0.06
     спроб
    -0.06
    _stderr
    -0.06
     scenario
    -0.06
     général
    -0.06
    POSITIVE LOGITS
    GreaterThan
    0.08
     Buffett
    0.08
    Richard
    0.07
    -widgets
    0.07
    ={`${
    0.07
    /on
    0.07
    」の
    0.07
     discrete
    0.07
     �
    0.07
    transpose
    0.07
    Act Density 0.002%

    No Known Activations