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

    Neuronpedia

    INDEX
    Explanations

    Writing systems and symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    відом
    -0.08
     Yu
    -0.06
     Bright
    -0.06
    =$("#
    -0.06
    境
    -0.06
     Cbd
    -0.06
    _;
↵
    -0.06
    FullName
    -0.06
    hello
    -0.06
     Recovery
    -0.06
    POSITIVE LOGITS
     daring
    0.07
    esehen
    0.06
     ak
    0.06
    war
    0.06
    favor
    0.06
    uche
    0.06
    İL
    0.06
    uttle
    0.06
    ерб
    0.06
     leggings
    0.06
    Act Density 0.053%

    No Known Activations