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

    Neuronpedia

    INDEX
    Explanations

    skip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moistened
    0.39
     faithfulness
    0.38
     soaked
    0.38
    样
    0.38
    اکي
    0.38
     débit
    0.38
     değeri
    0.38
     دفتر
    0.37
     দুধ
    0.37
    รักษา
    0.37
    POSITIVE LOGITS
    skip
    0.71
     skip
    0.66
    Skip
    0.63
     Skip
    0.62
     skipped
    0.58
     skips
    0.58
     skipping
    0.54
     Skipping
    0.50
    abar
    0.48
     स्किप
    0.48
    Act Density 0.000%

    No Known Activations