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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Neither
    0.43
     neither
    0.39
     सिलसिले
    0.39
     Have
    0.39
    సూరు
    0.38
    óch
    0.38
    sville
    0.37
     Мне
    0.37
     Livermore
    0.37
     имају
    0.37
    POSITIVE LOGITS
     viewer
    0.38
     člov
    0.38
     خرا
    0.37
    Effect
    0.37
     دون
    0.37
    نج
    0.36
     melting
    0.36
     tua
    0.36
     Viewer
    0.36
     sottop
    0.36
    Act Density 0.002%

    No Known Activations