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

    Neuronpedia

    INDEX
    Explanations

    cure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pars
    -0.08
     notebooks
    -0.07
    Alan
    -0.07
    提问
    -0.07
     Rath
    -0.07
    ʲ
    -0.07
    workers
    -0.07
     eds
    -0.07
    	arg
    -0.07
     petrol
    -0.06
    POSITIVE LOGITS
     vivastreet
    0.07
     giấy
    0.07
    tempt
    0.07
     bend
    0.07
     inflict
    0.07
    곽
    0.07
     requestBody
    0.07
     buffalo
    0.07
    쾌
    0.07
    ceso
    0.07
    Act Density 0.017%

    No Known Activations