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

    Neuronpedia

    INDEX
    Explanations

    write

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pumping
    -0.07
     Highway
    -0.07
     [
    -0.06
    Thunder
    -0.06
     cười
    -0.06
     DIM
    -0.06
     ml
    -0.06
    set
    -0.06
     cos
    -0.06
     lông
    -0.06
    POSITIVE LOGITS
     Horm
    0.07
    -trigger
    0.07
     Audi
    0.07
     VAN
    0.06
    	password
    0.06
    	fn
    0.06
    ADMIN
    0.06
     ters
    0.06
     течение
    0.06
     sentenced
    0.06
    Act Density 0.043%

    No Known Activations