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

    Neuronpedia

    INDEX
    Explanations

    Dialogue involving turning/addressing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     selects
    -0.07
    Upper
    -0.06
    Telephone
    -0.06
     BUS
    -0.06
     Denied
    -0.06
    ablish
    -0.06
     Threshold
    -0.06
     Liberation
    -0.06
    skyt
    -0.06
    ोद
    -0.06
    POSITIVE LOGITS
     cutting
    0.06
    .PictureBox
    0.06
     Nhưng
    0.06
     국가
    0.06
     tě
    0.06
     особенно
    0.06
     konuş
    0.06
     Morris
    0.06
    ským
    0.06
     المل
    0.06
    Act Density 0.008%

    No Known Activations