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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _triangle
    -0.07
    _pan
    -0.07
    _PT
    -0.07
    adem
    -0.06
     policemen
    -0.06
    لیم
    -0.06
    DTO
    -0.06
    POR
    -0.06
     mans
    -0.06
    омет
    -0.06
    POSITIVE LOGITS
     supplemental
    0.07
     drastically
    0.07
     really
    0.06
     undergoing
    0.06
     brackets
    0.06
     incredibly
    0.06
     bullied
    0.06
     диаг
    0.06
     aside
    0.06
     price
    0.06
    Act Density 0.002%

    No Known Activations