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

    Neuronpedia

    INDEX
    Explanations

    negative control systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    öglichkeiten
    0.73
    anyard
    0.70
    ávání
    0.68
     कैप्शन
    0.67
     TextAppearance
    0.66
    ographique
    0.66
     collectionView
    0.66
    issage
    0.64
     ინტერ
    0.64
    说道
    0.64
    POSITIVE LOGITS
     tyrannical
    0.91
     totalitarian
    0.90
     ruthless
    0.88
     authoritarian
    0.82
     archaic
    0.81
     oligarch
    0.81
     hardcore
    0.79
     autocratic
    0.79
     stark
    0.78
     Nazi
    0.76
    Act Density 0.000%

    No Known Activations