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

    Neuronpedia

    INDEX
    Explanations

    document section markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     superstar
    0.43
     therapists
    0.42
    امت
    0.41
     stratég
    0.41
     उत्कृष्टता
    0.41
     सुपरस्टार
    0.40
     HDAC
    0.40
    اعدة
    0.39
     Mahomes
    0.39
     cementing
    0.39
    POSITIVE LOGITS
    った
    0.48
     го
    0.43
    ();
    0.42
    ():
    0.41
    ėje
    0.41
    ]):
    0.39
     :
    0.39
     и
    0.38
     incluido
    0.38
     和
    0.38
    Act Density 0.011%

    No Known Activations