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

    Neuronpedia

    INDEX
    Explanations

    qualities and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     परेशान
    0.28
     contribution
    0.27
     task
    0.27
     Essay
    0.27
     novice
    0.26
    此类
    0.26
    வ்வாறு
    0.26
     article
    0.26
     tn
    0.26
     Task
    0.25
    POSITIVE LOGITS
     आणि
    0.50
     και
    0.50
     и
    0.49
    และความ
    0.48
     và
    0.47
     અને
    0.47
     और
    0.46
    και
    0.45
     and
    0.44
     și
    0.42
    Act Density 0.518%

    No Known Activations