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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     отличаются
    -0.08
     संचालन
    -0.08
     عملی
    -0.08
     Basis
    -0.08
     Gewicht
    -0.08
    opleiding
    -0.07
    _WEIGHT
    -0.07
     आरो
    -0.07
    (seed
    -0.07
     भार
    -0.07
    POSITIVE LOGITS
     windshield
    0.10
     cigarettes
    0.09
    屏
    0.08
     vats
    0.08
     കണ്ണ
    0.08
    �
    0.08
    藏
    0.08
     lenses
    0.08
     startled
    0.08
    کتے
    0.08
    Act Density 0.004%

    No Known Activations