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

    Neuronpedia

    INDEX
    Explanations

    agnostic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    beck
    0.41
    行
    0.39
     lectured
    0.38
    ctal
    0.37
    azan
    0.37
    ट्रा
    0.37
    alach
    0.36
    BE
    0.36
     কমপ্লে
    0.36
    mitted
    0.35
    POSITIVE LOGITS
     położ
    0.39
     Magdalena
    0.39
    નેસ
    0.37
    nes
    0.37
    엇
    0.37
    ès
    0.37
     ABB
    0.37
    گل
    0.37
     Athena
    0.36
    неш
    0.36
    Act Density 0.001%

    No Known Activations