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

    Neuronpedia

    INDEX
    Explanations

    causality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guys
    -0.06
     jih
    -0.06
    	mkdir
    -0.06
     CBC
    -0.06
    .reload
    -0.06
     проек
    -0.06
     ベ
    -0.06
     Dut
    -0.06
    .std
    -0.06
     سپ
    -0.06
    POSITIVE LOGITS
     [<
    0.07
     fatalError
    0.07
     Excellent
    0.06
     universities
    0.06
     Eventually
    0.06
    Linux
    0.06
     intuition
    0.06
    <Input
    0.06
     ensl
    0.06
     blue
    0.06
    Act Density 0.001%

    No Known Activations