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

    Neuronpedia

    INDEX
    Explanations

    paper organization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oders
    -0.08
    ancell
    -0.07
    uspend
    -0.07
     JsonRequestBehavior
    -0.07
     Trace
    -0.07
    صلاح
    -0.07
     sourcing
    -0.07
    爬
    -0.06
     stall
    -0.06
     Allocation
    -0.06
    POSITIVE LOGITS
     Swedish
    0.07
    几十年
    0.07
    edish
    0.07
    確か
    0.06
     II
    0.06
    。”
    0.06
    볓
    0.06
    .experimental
    0.06
    ＊
    0.06
    ,h
    0.06
    Act Density 0.131%

    No Known Activations