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

    Neuronpedia

    INDEX
    Explanations

    code, technical explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఉపయోగ
    0.49
     ASCII
    0.47
     क्वेश्चंस
    0.43
    ケーション
    0.43
     venn
    0.42
     받는
    0.41
     aproximadamente
    0.40
     généralement
    0.40
     деятельности
    0.40
     सूचीबद्ध
    0.39
    POSITIVE LOGITS
    Decre
    0.44
    讓我們
    0.41
    ++,
    0.39
    نر
    0.39
    lu
    0.39
    ्य
    0.38
    Sl
    0.38
    डा
    0.38
    Never
    0.38
    Ư
    0.38
    Act Density 0.030%

    No Known Activations