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

    Neuronpedia

    INDEX
    Explanations

    comparison and assignment operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    그래서
    0.75
     forefront
    0.69
     Trans
    0.67
     그래서
    0.67
     Mund
    0.65
    ;
    0.65
    *,
    0.65
     Sans
    0.64
     Meanwhile
    0.64
     пусть
    0.63
    POSITIVE LOGITS
     !=
    2.44
     ==
    2.25
     !==
    2.07
     >=
    1.99
    !=
    1.80
    =='
    1.77
    ==
    1.76
    ()==
    1.75
     =='
    1.71
    !='
    1.70
    Act Density 1.061%

    No Known Activations