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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    治疗
    -0.07
     engraved
    -0.07
    (va
    -0.06
    γραφή
    -0.06
    џџџџџџџџџџџџџџџџџџџџџџџџџџџџџџџџ
    -0.06
    赤
    -0.06
    !=-
    -0.06
    анка
    -0.06
     =================================
    -0.06
     unregister
    -0.06
    POSITIVE LOGITS
    /use
    0.07
     drama
    0.06
    cimal
    0.06
     geopol
    0.06
    gmail
    0.06
    lide
    0.06
     trợ
    0.06
    ाइ
    0.06
    (answer
    0.06
     През
    0.06
    Act Density 0.255%

    No Known Activations