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

    Neuronpedia

    INDEX
    Explanations

    them

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .close
    -0.07
     -*-
↵
    -0.07
     định
    -0.06
    <form
    -0.06
     önc
    -0.06
    	number
    -0.06
     SAX
    -0.06
    *w
    -0.06
    	println
    -0.06
    .carousel
    -0.06
    POSITIVE LOGITS
    abor
    0.07
     neuen
    0.07
     recycled
    0.07
     الولايات
    0.07
     Christine
    0.06
    ung
    0.06
     interfaces
    0.06
    Unt
    0.06
     득
    0.06
     unfore
    0.06
    Act Density 0.065%

    No Known Activations