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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     people
    -0.07
    (exc
    -0.07
     فس
    -0.07
     HTC
    -0.06
    BAL
    -0.06
     giden
    -0.06
    	se
    -0.06
    innerText
    -0.06
     Fiat
    -0.06
     QUAL
    -0.06
    POSITIVE LOGITS
    ávací
    0.08
     two
    0.07
     four
    0.07
     seven
    0.06
     six
    0.06
    .functional
    0.06
     Three
    0.06
     three
    0.06
    (training
    0.06
     five
    0.06
    Act Density 0.047%

    No Known Activations