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

    Neuronpedia

    INDEX
    Explanations

    highlights advancing objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     গ্রামে
    0.53
     ニュー
    0.51
     TNumber
    0.47
     insegn
    0.47
     учитель
    0.46
     apprend
    0.46
     tagReport
    0.46
    Ս
    0.46
     traduction
    0.45
     உருவா
    0.45
    POSITIVE LOGITS
     propellers
    0.44
    hstack
    0.42
     tapered
    0.41
     sightseeing
    0.40
     الاثنين
    0.40
    लीवुड
    0.40
    èbre
    0.40
    abilité
    0.38
     standstill
    0.38
    aphazard
    0.38
    Act Density 0.006%

    No Known Activations