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

    Neuronpedia

    INDEX
    Explanations

    go, run, visiting, pin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gaan
    0.38
     Latino
    0.37
    ದಯ
    0.37
    ㄣ
    0.37
     sajana
    0.37
     actu
    0.37
     caminar
    0.36
     wavefront
    0.36
    ularis
    0.36
    πτυ
    0.36
    POSITIVE LOGITS
     Boxes
    0.43
     Ebony
    0.42
    Took
    0.39
     বিনি
    0.39
    ంగ్
    0.38
     Baldwin
    0.38
     Само
    0.38
     προσωπ
    0.38
    到了
    0.37
     되었
    0.37
    Act Density 0.000%

    No Known Activations