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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ([]);↵
    -0.07
     Flint
    -0.07
     Щ
    -0.06
     yasak
    -0.06
    .toByteArray
    -0.06
     werde
    -0.06
    972
    -0.06
     普通
    -0.06
    .hasClass
    -0.06
     dateString
    -0.06
    POSITIVE LOGITS
     sake
    0.11
    ै।↵
    0.07
    ime
    0.07
    .gridView
    0.06
    ."↵↵↵
    0.06
    !)
    0.06
    rowad
    0.06
     klim
    0.06
    median
    0.06
    .”↵
    0.06
    Act Density 0.005%

    No Known Activations