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

    Neuronpedia

    INDEX
    Explanations

    fast fashion brands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dealt
    0.53
    akespeare
    0.52
    ancher
    0.51
    than
    0.50
    شد
    0.50
     aran
    0.49
     publishes
    0.49
    clothes
    0.48
    UTURE
    0.48
    tum
    0.48
    POSITIVE LOGITS
    ｌ
    0.60
     montre
    0.57
    𝒍
    0.57
    仿佛
    0.55
    ным
    0.54
     forêts
    0.54
    LECTION
    0.53
    ंझ
    0.52
    Mountain
    0.52
     приема
    0.52
    Act Density 0.000%

    No Known Activations