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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的优势
    -0.08
    ashion
    -0.07
     Dem
    -0.07
    (require
    -0.07
     Sylv
    -0.06
    SON
    -0.06
    ホテル
    -0.06
    范围内
    -0.06
     ===>
    -0.06
    [NUM
    -0.06
    POSITIVE LOGITS
    .Note
    0.07
    	area
    0.07
    arding
    0.07
    ि
    0.07
    �
    0.07
    $results
    0.07
    _element
    0.07
    噩
    0.07
     ah
    0.07
     после
    0.07
    Act Density 0.004%

    No Known Activations