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

    Neuronpedia

    INDEX
    Explanations

    these

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cela
    0.48
     aquel
    0.44
     данным
    0.41
     אותו
    0.40
     সেটাই
    0.40
     bunun
    0.39
     tega
    0.39
     tät
    0.38
     buna
    0.38
     اهو
    0.37
    POSITIVE LOGITS
     these
    4.19
    这些
    3.88
    these
    3.88
    これらの
    3.84
    這些
    3.73
    These
    3.72
     These
    3.48
     этих
    3.44
     THESE
    3.38
     эти
    3.33
    Act Density 0.131%

    No Known Activations