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

    Neuronpedia

    INDEX
    Explanations

    #endif

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    531
    -0.07
     Chronicles
    -0.07
    真是
    -0.07
     Таким
    -0.06
    CES
    -0.06
    �
    -0.06
    ("&
    -0.06
    -leaning
    -0.06
    (pa
    -0.06
    [];↵
    -0.06
    POSITIVE LOGITS
     доз
    0.07
    ,max
    0.07
    �
    0.06
    .Diff
    0.06
    ,width
    0.06
     proprietary
    0.06
    房屋
    0.06
    чат
    0.06
    僅
    0.06
     البي
    0.06
    Act Density 0.002%

    No Known Activations