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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    testCase
    -0.07
    ն
    -0.07
    	token
    -0.06
     Reported
    -0.06
    上网
    -0.06
    [rand
    -0.06
    ilename
    -0.06
    .Floor
    -0.06
    กร
    -0.06
     Leben
    -0.06
    POSITIVE LOGITS
    restaurant
    0.07
    צרפת
    0.07
    (|
    0.07
    安定
    0.07
    +"</
    0.07
    "/>.</
    0.07
    自助
    0.07
    .Uri
    0.07
    阴影
    0.06
    Experimental
    0.06
    Act Density 0.051%

    No Known Activations