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

    Neuronpedia

    INDEX
    Explanations

    Nepal: Sherpas, Shahs, greenery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fetching
    0.39
    取扱
    0.39
    휩
    0.37
    执行
    0.37
     reconstructed
    0.37
     inflamed
    0.37
    ճ
    0.37
     उत्पन्न
    0.36
    )=>{
    0.36
    ){
    0.35
    POSITIVE LOGITS
     Gur
    0.81
    Gur
    0.75
     gur
    0.61
     मगर
    0.60
     গুরু
    0.59
     गुरु
    0.59
     गुरू
    0.55
    gur
    0.54
     Lim
    0.50
     magar
    0.50
    Act Density 0.002%

    No Known Activations