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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    くれた
    -0.07
     помощи
    -0.07
     appreciate
    -0.06
    няття
    -0.06
     Sticky
    -0.06
    tracted
    -0.06
     وحدة
    -0.06
    	T
    -0.06
    pressure
    -0.06
     humidity
    -0.06
    POSITIVE LOGITS
     Forg
    0.07
     Enumerable
    0.07
    camel
    0.07
     Cheng
    0.06
    <Box
    0.06
     który
    0.06
     ödeme
    0.06
    <ul
    0.06
    ΟΥΛ
    0.06
    ClassLoader
    0.06
    Act Density 0.001%

    No Known Activations