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

    Neuronpedia

    INDEX
    Explanations

    structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XY
    -0.06
    eny
    -0.06
     зуп
    -0.06
    ru
    -0.06
    keeper
    -0.06
    >Nama
    -0.06
    chat
    -0.06
     Jerry
    -0.06
    DI
    -0.06
    建設
    -0.06
    POSITIVE LOGITS
     групп
    0.08
     рассказ
    0.08
     medal
    0.06
    ‰
    0.06
    	port
    0.06
     اطل
    0.06
    坦
    0.06
    ongo
    0.06
     т
    0.06
     الجه
    0.06
    Act Density 0.020%

    No Known Activations