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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     endl
    -0.09
     Btn
    -0.08
    繇
    -0.07
     FAA
    -0.07
     ApiController
    -0.07
    	strcpy
    -0.07
     Gupta
    -0.07
    .trailing
    -0.07
    )sender
    -0.07
     дор
    -0.07
    POSITIVE LOGITS
    ensemble
    0.07
    沦
    0.07
    phant
    0.07
    لج
    0.06
    nym
    0.06
    kim
    0.06
    沁
    0.06
     deployment
    0.06
    Pred
    0.06
     dịch
    0.06
    Act Density 0.020%

    No Known Activations