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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المل
    -0.07
    obel
    -0.07
     brown
    -0.07
     charm
    -0.06
    ，是
    -0.06
    Language
    -0.06
     يس
    -0.06
     查询
    -0.06
    ilia
    -0.06
    acting
    -0.06
    POSITIVE LOGITS
    QUOTE
    0.07
     [=[
    0.07
     personn
    0.06
     právě
    0.06
     všechno
    0.06
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.06
     pstmt
    0.06
     DK
    0.06
     �
    0.06
    Baş
    0.06
    Act Density 0.019%

    No Known Activations