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

    Neuronpedia

    INDEX
    Explanations

    introduces lists or breakdowns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </tbody>
    0.91
    以及
    0.83
     różnych
    0.83
     Various
    0.82
     }}$.
    0.82
     বিভিন্ন
    0.80
    および
    0.80
    <start_of_image>
    0.80
     различных
    0.79
    <unused2146>
    0.79
    POSITIVE LOGITS
    :
    1.23
    :<
    1.00
     firstly
    0.92
     :
    0.92
    :-
    0.89
    :*
    0.89
    :“
    0.87
    ;:
    0.83
    ;
    0.82
    :~
    0.81
    Act Density 0.110%

    No Known Activations