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

    Neuronpedia

    INDEX
    Explanations

    settings, selection, and adjustments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prostit
    0.53
     адво
    0.52
     Gründung
    0.52
    資本
    0.51
     interdiscipl
    0.51
     traged
    0.50
    asyarakat
    0.50
     kriminal
    0.50
    社會
    0.50
    AssetsResponse
    0.49
    POSITIVE LOGITS
     settings
    1.10
     Settings
    1.04
     control
    0.97
     adjustable
    0.97
    调节
    0.91
     Control
    0.91
     настройки
    0.88
    Settings
    0.87
     Adjustable
    0.87
     setting
    0.86
    Act Density 0.200%

    No Known Activations