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

    Neuronpedia

    INDEX
    Explanations

    shrinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DIP
    -0.06
    ष
    -0.06
     тепло
    -0.06
    benh
    -0.06
    سو
    -0.06
     layoutParams
    -0.06
    tour
    -0.06
     лим
    -0.06
    JP
    -0.06
    up
    -0.06
    POSITIVE LOGITS
     running
    0.07
    -{
    0.07
    _factors
    0.07
    TestMethod
    0.07
    <Document
    0.06
     universe
    0.06
    /products
    0.06
     Thrones
    0.06
    	iNdEx
    0.06
    plement
    0.06
    Act Density 0.005%

    No Known Activations