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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ancestor
    -0.08
     call
    -0.07
     managing
    -0.07
    ANG
    -0.07
    RowCount
    -0.07
    .*↵↵
    -0.07
    Pair
    -0.07
     ancestors
    -0.07
    	score
    -0.07
    yen
    -0.06
    POSITIVE LOGITS
    ��
    0.07
    くん
    0.07
    пе
    0.06
    885
    0.06
     vivastreet
    0.06
    393
    0.06
    şt
    0.06
    "]=>
    0.06
    �
    0.06
     Released
    0.06
    Act Density 0.057%

    No Known Activations