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

    Neuronpedia

    INDEX
    Explanations

    thrust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vät
    0.96
    ्टर
    0.80
    voren
    0.80
    oises
    0.79
     gắn
    0.78
     protagon
    0.77
    tractor
    0.77
    ्तिक
    0.77
    larni
    0.77
    μάτων
    0.76
    POSITIVE LOGITS
    در
    0.88
     طی
    0.87
    T
    0.79
    Food
    0.76
    ó
    0.75
    ރ
    0.75
    Х
    0.73
    ও
    0.73
    ال
    0.72
     क्वांटिटी
    0.72
    Act Density 0.000%

    No Known Activations