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

    Neuronpedia

    INDEX
    Explanations

    Flow Graphs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ดูแล
    0.79
     값을
    0.77
     তাজ
    0.70
    Microelectronics
    0.68
     biochemical
    0.68
    டியான
    0.67
    トマト
    0.67
    Ｃ
    0.66
    睑
    0.66
     нулю
    0.66
    POSITIVE LOGITS
    ßer
    0.64
    spiral
    0.62
    Sí
    0.58
    Rue
    0.58
    Retrieve
    0.57
    রাগ
    0.57
    तोष
    0.57
     spiral
    0.56
    <0xC6>
    0.55
     curly
    0.55
    Act Density 0.724%

    No Known Activations