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

    Neuronpedia

    INDEX
    Explanations

    os

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    charged
    -0.07
    ディ
    -0.07
     daß
    -0.06
     FAST
    -0.06
    .Strict
    -0.06
    ной
    -0.06
    length
    -0.06
     comple
    -0.06
    .InvariantCulture
    -0.06
    POSITIVE LOGITS
     os
    0.21
    (os
    0.11
    	os
    0.10
     aos
    0.09
    .OS
    0.09
    Os
    0.09
    os
    0.09
    OS
    0.08
     Os
    0.08
    "os
    0.08
    Act Density 0.008%

    No Known Activations