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

    Neuronpedia

    INDEX
    Explanations

    delve deeper into a specific aspect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    两个
    0.89
    兩個
    0.87
    two
    0.86
     aspect
    0.85
    aspect
    0.84
     दोन
    0.81
     telah
    0.80
     two
    0.79
     Two
    0.77
     mata
    0.75
    POSITIVE LOGITS
    بھی
    0.91
     cualquier
    0.90
    obr
    0.89
    좁
    0.89
    谍
    0.89
    ラック
    0.88
     classifier
    0.87
     cualquiera
    0.87
     cómo
    0.86
    ötet
    0.86
    Act Density 0.025%

    No Known Activations