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

    Neuronpedia

    INDEX
    Explanations

    time markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ىڭ
    0.93
     সিরিজের
    0.89
     nguồn
    0.87
    xmin
    0.87
    ilibr
    0.84
     یافته
    0.84
    INPUT
    0.83
    বাব
    0.82
    CRS
    0.81
    van
    0.81
    POSITIVE LOGITS
    共同
    1.32
    一起
    1.30
    一同
    1.30
     together
    1.15
     मिलकर
    1.14
     சேர்ந்து
    1.13
     menuju
    1.10
     diskusi
    1.09
     juntos
    1.09
     strolling
    1.04
    Act Density 0.441%

    No Known Activations