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

    Neuronpedia

    INDEX
    Explanations

    pattern type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗡
    0.44
     لڑکی
    0.44
    निम्नलिखित
    0.42
    坩
    0.41
    สินค้า
    0.41
    avacanam
    0.41
     महिलाओं
    0.40
    ทำงาน
    0.40
    𝗙
    0.40
     работал
    0.40
    POSITIVE LOGITS
     type
    0.51
     option
    0.51
     options
    0.48
    Type
    0.46
     Type
    0.46
     train
    0.43
     d
    0.43
     to
    0.42
     halides
    0.42
     getType
    0.41
    Act Density 0.000%

    No Known Activations