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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     드립니다
    -0.07
    363
    -0.06
     First
    -0.06
     perder
    -0.06
    732
    -0.06
     ker
    -0.06
    icode
    -0.06
    Girl
    -0.06
    [df
    -0.06
    ков
    -0.06
    POSITIVE LOGITS
    (html
    0.07
    WAYS
    0.07
    ,ep
    0.06
    ocene
    0.06
    IVERS
    0.06
     демон
    0.06
     OU
    0.06
    الش
    0.06
     Trie
    0.06
    aporation
    0.06
    Act Density 0.018%

    No Known Activations