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

    Neuronpedia

    INDEX
    Explanations

    key concepts and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mj
    0.23
    zan
    0.21
     বিষয়টা
    0.21
    idez
    0.21
    urus
    0.21
    zig
    0.21
     включая
    0.20
    iis
    0.20
     SU
    0.20
    陆续
    0.20
    POSITIVE LOGITS
     fraught
    0.36
    の一つ
    0.34
     unto
    0.33
     которому
    0.32
    之一
    0.32
    的一部分
    0.31
     deserving
    0.31
     자체가
    0.31
     જેને
    0.31
     जिसने
    0.30
    Act Density 0.162%

    No Known Activations