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
     Nom
    -0.07
     desks
    -0.07
     Ple
    -0.07
     besides
    -0.07
     next
    -0.07
     cutoff
    -0.06
    _Sub
    -0.06
     compar
    -0.06
     olig
    -0.06
    Pod
    -0.06
    POSITIVE LOGITS
     efforts
    0.07
    เทพ
    0.07
     لت
    0.07
    !");↵↵
    0.06
    ri
    0.06
     일이
    0.06
     розвит
    0.06
    CAA
    0.06
    …I
    0.06
     sorrow
    0.06
    Act Density 0.025%

    No Known Activations