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

    Neuronpedia

    INDEX
    Explanations

    competitions, championships, and outings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ან
    0.37
     όταν
    0.35
     amyg
    0.35
     belladone
    0.35
    電源
    0.34
    公元
    0.33
    คือ
    0.33
     coward
    0.32
     murió
    0.32
     glared
    0.32
    POSITIVE LOGITS
     competitions
    0.44
     Championships
    0.40
     outings
    0.39
     participating
    0.39
     competition
    0.38
     competit
    0.37
     opportunities
    0.36
     participates
    0.36
     Triathlon
    0.36
     students
    0.35
    Act Density 0.000%

    No Known Activations