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

    Neuronpedia

    INDEX
    Explanations

    answer is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مالی
    0.70
    гент
    0.68
     บริ
    0.65
     فوټبال
    0.64
     обращения
    0.64
     మంది
    0.63
    satellite
    0.60
    FEATURE
    0.60
     പുതിയ
    0.59
     satellite
    0.59
    POSITIVE LOGITS
    astos
    0.76
    遵循
    0.74
    elm
    0.74
    perp
    0.73
    鞆
    0.73
    yczy
    0.73
     norme
    0.72
    停车场
    0.72
     Simplify
    0.71
    机场
    0.68
    Act Density 0.007%

    No Known Activations