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

    Neuronpedia

    INDEX
    Explanations

    Adapter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    想不到
    -0.08
     Duo
    -0.07
    魅
    -0.07
    Unlike
    -0.07
    gcd
    -0.07
    _restart
    -0.07
     Carnival
    -0.07
    统筹推进
    -0.07
    jug
    -0.07
    公顷
    -0.07
    POSITIVE LOGITS
    ис
    0.07
     nieruchomości
    0.07
    _locations
    0.07
     LOCATION
    0.07
    .ie
    0.07
     AJ
    0.07
    积极性
    0.07
    IFY
    0.07
    涂抹
    0.07
    位置
    0.07
    Act Density 0.002%

    No Known Activations