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

    Neuronpedia

    INDEX
    Explanations

    symptoms overlap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     చేస్తుంది
    0.88
    స్తుంది
    0.79
    Has
    0.79
    Does
    0.79
     начинает
    0.77
     Wants
    0.76
     Sees
    0.75
     következő
    0.74
     করছে
    0.73
     Gets
    0.73
    POSITIVE LOGITS
     are
    2.10
     aren
    1.70
     have
    1.61
     provide
    1.58
     require
    1.58
     were
    1.57
     contribute
    1.47
     đều
    1.39
     offer
    1.38
     jsou
    1.35
    Act Density 0.873%

    No Known Activations