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

    Neuronpedia

    INDEX
    Explanations

    governance and leadership

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ahi
    -0.07
    .moveToFirst
    -0.07
    .baidu
    -0.07
    ää
    -0.07
    .ge
    -0.06
    쟤
    -0.06
     swe
    -0.06
    -decoration
    -0.06
    	X
    -0.06
    _again
    -0.06
    POSITIVE LOGITS
     bolts
    0.08
     capacities
    0.07
    .fixture
    0.07
     institutional
    0.07
    是要
    0.07
    트
    0.07
    一场
    0.07
    Physical
    0.06
    逐渐
    0.06
     Antony
    0.06
    Act Density 0.113%

    No Known Activations