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

    Neuronpedia

    INDEX
    Explanations

    start open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oz
    -0.07
    -has
    -0.07
    ayette
    -0.07
     Ich
    -0.07
     issue
    -0.07
     onView
    -0.07
     Made
    -0.07
    Save
    -0.07
     creating
    -0.07
    olve
    -0.07
    POSITIVE LOGITS
    氩
    0.08
    HI
    0.07
    护卫
    0.07
    슌
    0.07
    陪着
    0.07
    殉
    0.07
    .Quantity
    0.07
     dear
    0.07
    띵
    0.07
    讚
    0.07
    Act Density 0.010%

    No Known Activations