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

    Neuronpedia

    INDEX
    Explanations

    measurement indicators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getCode
    -0.07
     前
    -0.07
    (Link
    -0.06
    120
    -0.06
    /status
    -0.06
    胜
    -0.06
    .review
    -0.06
     lotion
    -0.06
    ictim
    -0.06
     predecessor
    -0.06
    POSITIVE LOGITS
    ]';↵
    0.07
    )',↵
    0.07
     reflects
    0.06
     ));
    0.06
     Markup
    0.06
    .Linked
    0.06
    едаг
    0.06
    	static
    0.06
    	echo
    0.06
     م
    0.06
    Act Density 0.032%

    No Known Activations