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

    Neuronpedia

    INDEX
    Explanations

    code variable names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     系
    -0.07
     showers
    -0.07
    circle
    -0.07
    ฮ
    -0.07
    něl
    -0.06
    Markers
    -0.06
     brigade
    -0.06
     alloys
    -0.06
     designer
    -0.06
     Lloyd
    -0.06
    POSITIVE LOGITS
     tiểu
    0.07
    <g
    0.06
     gentle
    0.06
     kö
    0.06
     hypothetical
    0.06
     assert
    0.06
    area
    0.06
     reserva
    0.06
     Py
    0.06
    _agents
    0.06
    Act Density 0.007%

    No Known Activations