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

    Neuronpedia

    INDEX
    Explanations

    OT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    스를
    -0.07
     K
    -0.07
     Box
    -0.07
     correctly
    -0.06
    她的
    -0.06
    訊
    -0.06
    -CS
    -0.06
    uster
    -0.06
     نخست
    -0.06
    (QIcon
    -0.06
    POSITIVE LOGITS
    	Assert
    0.07
    /loose
    0.06
    　　　　　　　　
    0.06
    845
    0.06
    Atlantic
    0.06
     poisoned
    0.06
     Experienced
    0.06
     Razor
    0.06
    	parse
    0.06
    (csv
    0.06
    Act Density 0.001%

    No Known Activations