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

    Neuronpedia

    INDEX
    Explanations

    Analyzing components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đây
    -0.07
     England
    -0.07
    景色
    -0.07
     Defense
    -0.07
    GLIGENCE
    -0.07
    !)
    -0.07
     contains
    -0.07
    IRMWARE
    -0.07
     barren
    -0.07
     parish
    -0.06
    POSITIVE LOGITS
    ⓞ
    0.08
    纫
    0.07
    SelectedItem
    0.07
    ⓛ
    0.07
    𝙤
    0.07
     wij
    0.07
    calling
    0.07
     punching
    0.06
    겪
    0.06
    .`);↵
    0.06
    Act Density 0.072%

    No Known Activations