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

    Neuronpedia

    INDEX
    Explanations

    Date

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ellant
    -0.08
     fs
    -0.08
     cell
    -0.08
    _pt
    -0.07
     exposure
    -0.07
    transfer
    -0.07
    du
    -0.07
    招标
    -0.07
     Plaintiff
    -0.07
    ﺩ
    -0.07
    POSITIVE LOGITS
     wherever
    0.10
    .Q
    0.08
    ।
    0.08
    趟
    0.07
    ).</
    0.07
     możli
    0.07
    精品
    0.07
    一趟
    0.07
    /orders
    0.07
     Successfully
    0.07
    Act Density 0.006%

    No Known Activations