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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الك
    0.29
    iyoruz
    0.29
     ٣
    0.28
    <0x0D>
    0.27
    ">${
    0.26
     второй
    0.26
     kuhusu
    0.26
     về
    0.26
     تك
    0.26
     జీవిత
    0.26
    POSITIVE LOGITS
    ט
    0.26
    have
    0.25
    loose
    0.24
     addiction
    0.23
     ahli
    0.23
    A
    0.23
     decentral
    0.23
    u
    0.23
     synchron
    0.23
    ain
    0.22
    Act Density 0.031%

    No Known Activations