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

    Neuronpedia

    INDEX
    Explanations

    Code related to interfaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     franchise
    -0.08
     primitive
    -0.07
    .responses
    -0.07
    -generic
    -0.07
    .dataGridViewTextBoxColumn
    -0.07
     protests
    -0.07
     rừng
    -0.07
    Response
    -0.07
    EATURE
    -0.07
    .ViewGroup
    -0.07
    POSITIVE LOGITS
    𝘬
    0.07
    רה
    0.07
     başlat
    0.06
    ולל
    0.06
     FPGA
    0.06
    מרה
    0.06
    퓐
    0.06
    mega
    0.06
     weekly
    0.06
     bác
    0.06
    Act Density 0.005%

    No Known Activations