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

    Neuronpedia

    INDEX
    Explanations

    states

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    comes
    -0.07
    801
    -0.07
    _almost
    -0.07
    显
    -0.06
     burst
    -0.06
    同
    -0.06
    Sunday
    -0.06
     Check
    -0.06
     同
    -0.06
     Investing
    -0.06
    POSITIVE LOGITS
    .barDockControl
    0.07
    ++){↵
    0.06
     lum
    0.06
    .findAll
    0.06
    agne
    0.06
     bury
    0.06
     Palo
    0.06
     дані
    0.06
     STDCALL
    0.06
    ,class
    0.06
    Act Density 0.013%

    No Known Activations