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

    Neuronpedia

    INDEX
    Explanations

    incarnation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     силь
    -0.07
    <Edge
    -0.07
     Bayesian
    -0.06
    xaf
    -0.06
    щий
    -0.06
    jos
    -0.06
     alarms
    -0.06
     scheduler
    -0.06
    альные
    -0.06
    herence
    -0.06
    POSITIVE LOGITS
     incarnation
    0.11
     incarn
    0.09
     Concurrent
    0.07
     franchise
    0.07
     concurrent
    0.07
     İt
    0.07
    arnation
    0.06
     ogs
    0.06
    @
    0.06
     reinc
    0.06
    Act Density 0.002%

    No Known Activations