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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     will
    -0.09
     may
    -0.08
     can
    -0.08
     would
    -0.08
     has
    -0.08
    'd
    -0.08
     had
    -0.07
     gave
    -0.07
    can
    -0.07
    Can
    -0.07
    POSITIVE LOGITS
    MG
    0.07
    !?
    0.07
    .setImage
    0.06
    知识
    0.06
    ctype
    0.06
     setImage
    0.06
    	plt
    0.06
    VK
    0.06
    条件
    0.06
     ★
    0.06
    Act Density 0.018%

    No Known Activations