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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    أة
    -0.07
    좌
    -0.06
    .manager
    -0.06
    (cx
    -0.06
    _PUSH
    -0.06
    ODEV
    -0.06
     mint
    -0.06
     lasting
    -0.06
     Bra
    -0.06
    ，则
    -0.06
    POSITIVE LOGITS
    操作
    0.07
    wright
    0.07
     Lol
    0.07
     suspicious
    0.07
    وتی
    0.06
    -content
    0.06
    になって
    0.06
     cout
    0.06
    plotlib
    0.06
     аж
    0.06
    Act Density 0.000%

    No Known Activations