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

    Neuronpedia

    INDEX
    Explanations

    do that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estos
    1.77
     these
    1.69
    these
    1.61
     estas
    1.59
    These
    1.57
     aceste
    1.57
    これらの
    1.53
     queste
    1.53
    这些
    1.49
    這些
    1.45
    POSITIVE LOGITS
    That
    3.70
     That
    3.63
     that
    3.36
    that
    3.35
     thats
    3.27
     THAT
    3.19
     Thats
    3.15
    THAT
    2.88
    thats
    2.86
    Thats
    2.82
    Act Density 0.594%

    No Known Activations