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

    Neuronpedia

    INDEX
    Explanations

    surrounding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    标题
    -0.06
    wish
    -0.06
     Nolan
    -0.06
     pense
    -0.06
    /render
    -0.06
    ॉल
    -0.06
    __)
    -0.06
     NH
    -0.06
    osals
    -0.06
     easier
    -0.06
    POSITIVE LOGITS
     surrounding
    0.09
     สถาน
    0.06
    dr
    0.06
    üslüman
    0.06
    피
    0.06
    (Mouse
    0.06
     따른
    0.06
    .TRAILING
    0.06
     절
    0.06
     devastation
    0.06
    Act Density 0.006%

    No Known Activations