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

    Neuronpedia

    INDEX
    Explanations

    following `>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    да
    2.52
    ات
    1.94
    ্ড
    1.83
    б
    1.70
    к
    1.66
    يت
    1.64
    sentences
    1.63
     spinors
    1.63
    ⒎
    1.55
    েকের
    1.55
    POSITIVE LOGITS
    에
    2.05
    的情况
    1.85
    的问题
    1.71
    而是
    1.63
    的发展
    1.63
    IE
    1.62
    ০০
    1.60
    に
    1.59
    อะไร
    1.58
    PE
    1.57
    Act Density 0.114%

    No Known Activations