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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _Settings
    -0.08
    bedPane
    -0.07
    _Create
    -0.07
    造型
    -0.07
    统治
    -0.07
    _mutex
    -0.07
     Mesa
    -0.07
    _Selected
    -0.07
    إبد
    -0.07
    ellungen
    -0.07
    POSITIVE LOGITS
    受到
    0.07
    IES
    0.07
    	expect
    0.07
     Fed
    0.06
     Saving
    0.06
    ier
    0.06
    >();↵↵
    0.06
     Gauge
    0.06
     AccessToken
    0.06
     expected
    0.06
    Act Density 0.011%

    No Known Activations