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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yüz
    -0.07
     informations
    -0.06
     desn
    -0.06
    /temp
    -0.06
     Nice
    -0.06
     لح
    -0.06
     burns
    -0.06
     informací
    -0.06
    	fflush
    -0.06
     suits
    -0.06
    POSITIVE LOGITS
    クション
    0.06
    Conflict
    0.06
     dns
    0.06
     Solo
    0.06
    asmus
    0.06
    apur
    0.06
    CAD
    0.06
     Sabbath
    0.06
    (tx
    0.06
     наш
    0.06
    Act Density 0.001%

    No Known Activations