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

    Neuronpedia

    INDEX
    Explanations

    data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [player
    -0.07
    .serv
    -0.07
     tourism
    -0.06
     �
    -0.06
     Cost
    -0.06
                    
    -0.06
    	full
    -0.06
    (back
    -0.06
     Mısır
    -0.06
     Hits
    -0.06
    POSITIVE LOGITS
    くら
    0.08
    ä
    0.06
     виробництва
    0.06
    クト
    0.06
    -datepicker
    0.06
    ิกา
    0.06
     güneş
    0.06
    >';↵↵
    0.06
    すぐ
    0.06
     itch
    0.06
    Act Density 0.046%

    No Known Activations