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

    Neuronpedia

    INDEX
    Explanations

    gravitational waves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tyrannical
    0.66
     функції
    0.61
     أعمال
    0.57
     програм
    0.57
     функцию
    0.57
     පිළ
    0.57
     zeroth
    0.57
     пат
    0.55
     harán
    0.55
    ுள்ளார்
    0.55
    POSITIVE LOGITS
    In
    0.61
    Syn
    0.60
    History
    0.60
    Ре
    0.56
    Се
    0.56
    История
    0.55
    pg
    0.54
    Time
    0.54
    Ed
    0.54
    Fin
    0.53
    Act Density 0.005%

    No Known Activations