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

    Neuronpedia

    INDEX
    Explanations

    human complexity and uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    敵人
    0.56
    敌人
    0.48
     निर्माता
    0.47
    BUY
    0.42
    部份
    0.42
     Contractor
    0.42
     enemigos
    0.42
     foe
    0.41
     bukti
    0.41
     enemigo
    0.40
    POSITIVE LOGITS
    human
    0.44
    immers
    0.44
     human
    0.43
    complexity
    0.41
    Human
    0.40
    tim
    0.40
    So
    0.38
    e
    0.38
    layers
    0.37
    elastic
    0.37
    Act Density 0.000%

    No Known Activations