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

    Neuronpedia

    INDEX
    Explanations

    writing prompts and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yılında
    0.39
     مرگ
    0.36
    Oklahoma
    0.35
    英語版
    0.35
     جنب
    0.34
    alog
    0.34
     नतीजा
    0.34
    ucs
    0.34
     wikipedia
    0.34
    i
    0.34
    POSITIVE LOGITS
     ጭ
    0.45
    გრამ
    0.39
    ঝ
    0.38
     كذلك
    0.38
    他說
    0.38
    र्दशी
    0.38
     cheese
    0.37
    𝑆
    0.37
    న
    0.37
    श्यक
    0.37
    Act Density 0.001%

    No Known Activations