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

    Neuronpedia

    INDEX
    Explanations

    ibr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ONUS
    -0.07
     Sheets
    -0.07
     worden
    -0.07
     agar
    -0.07
    å
    -0.07
    =time
    -0.06
     está
    -0.06
     cru
    -0.06
    Stride
    -0.06
     reign
    -0.06
    POSITIVE LOGITS
     Vladimir
    0.07
    ."+
    0.06
    setMax
    0.06
    ",[
    0.06
     сіль
    0.06
    addr
    0.06
     squarely
    0.06
    exclusive
    0.06
    ніп
    0.06
    925
    0.06
    Act Density 0.001%

    No Known Activations