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

    Neuronpedia

    INDEX
    Explanations

    survive

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Transit
    -0.07
    	Route
    -0.06
     rugged
    -0.06
     �
    -0.06
    (reason
    -0.06
    atype
    -0.06
     Regarding
    -0.06
    using
    -0.06
     четвер
    -0.06
    (queue
    -0.06
    POSITIVE LOGITS
     spolup
    0.07
     вит
    0.07
    “Well
    0.07
     Россий
    0.07
    .ev
    0.07
    ******↵
    0.06
     本
    0.06
     ราคา
    0.06
    šov
    0.06
    本
    0.06
    Act Density 0.018%

    No Known Activations