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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     страна
    -0.08
     ميل
    -0.08
     നില
    -0.08
    .Valid
    -0.08
     MS
    -0.07
     refr
    -0.07
    	ms
    -0.07
     хранения
    -0.07
     dagelijkse
    -0.07
    coin
    -0.07
    POSITIVE LOGITS
     जाकर
    0.10
     তদন্ত
    0.10
    赴
    0.10
     investigate
    0.09
     ಭೇಟಿ
    0.09
    调查
    0.09
    到
    0.09
     intervenir
    0.09
     барып
    0.09
    巡视
    0.08
    Act Density 0.073%

    No Known Activations