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

    Neuronpedia

    INDEX
    Explanations

    law summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ่ม
    -0.07
     तथ
    -0.06
     ม
    -0.06
     Aj
    -0.06
     Seit
    -0.06
     tiled
    -0.06
    loss
    -0.06
     dwarf
    -0.06
     bilg
    -0.06
     Claud
    -0.06
    POSITIVE LOGITS
    .textLabel
    0.08
    Retention
    0.07
     причины
    0.07
    COMMON
    0.06
     IData
    0.06
    中國
    0.06
     yüzden
    0.06
    anvas
    0.06
    -colored
    0.06
    taient
    0.06
    Act Density 0.012%

    No Known Activations