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

    Neuronpedia

    INDEX
    Explanations

    especially followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ので
    2.80
    Ƭ
    2.57
    ˒
    2.52
    Р
    2.43
    隍
    2.39
    ഗ്
    2.38
     суме
    2.35
    deos
    2.34
    了一个
    2.29
    ➳
    2.27
    POSITIVE LOGITS
    s
    3.07
    ы
    2.85
    ات
    2.68
    ع
    2.58
    ों
    2.48
    ের
    2.42
    nde
    2.36
    एस
    2.36
    j
    2.32
    ৫
    2.31
    Act Density 0.048%

    No Known Activations