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

    Neuronpedia

    INDEX
    Explanations

    `ve` followed by past participles or `provided`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    2.11
    yu
    1.91
    yer
    1.78
    yout
    1.77
    iation
    1.66
    u
    1.66
    iy
    1.65
    oo
    1.63
    wv
    1.63
    ians
    1.63
    POSITIVE LOGITS
    т
    1.74
    з
    1.45
    за
    1.29
    ТЕ
    1.29
    나
    1.26
    ım
    1.23
    нди
    1.23
     allgeme
    1.18
    ParentElement
    1.16
    ভাবে
    1.15
    Act Density 1.021%

    No Known Activations