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

    Neuronpedia

    INDEX
    Explanations

    temporal references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ствуют
    0.74
    cannot
    0.74
    ють
    0.71
     cannot
    0.71
     دارند
    0.71
     دارد
    0.70
     are
    0.69
     ندارد
    0.68
    Choose
    0.67
     છે
    0.64
    POSITIVE LOGITS
     initially
    1.34
     until
    1.33
     Until
    1.30
     était
    1.29
    でしたが
    1.24
     Initially
    1.22
     étaient
    1.20
     inicialmente
    1.20
    until
    1.18
     originally
    1.16
    Act Density 0.622%

    No Known Activations