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

    Neuronpedia

    INDEX
    Explanations

    wiggling, movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clar
    -0.06
    计算
    -0.06
     Shawn
    -0.06
     Charity
    -0.06
    andy
    -0.06
     Christie
    -0.06
     LINEAR
    -0.06
     banker
    -0.06
     Cav
    -0.06
     shaved
    -0.06
    POSITIVE LOGITS
    ]=>
    0.07
     hyperlink
    0.07
    KeyListener
    0.07
    Knowledge
    0.07
     lương
    0.06
    coll
    0.06
     různých
    0.06
    .SE
    0.06
    leans
    0.06
    _cfg
    0.06
    Act Density 0.011%

    No Known Activations