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

    Neuronpedia

    INDEX
    Explanations

    academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incel
    -0.07
     kendisini
    -0.07
     apl
    -0.07
    패
    -0.06
    sitemap
    -0.06
    ximo
    -0.06
    ULAR
    -0.06
    	ob
    -0.06
     زی
    -0.06
    @Path
    -0.06
    POSITIVE LOGITS
     enabling
    0.07
    類
    0.07
     acquired
    0.07
    \models
    0.06
     LOG
    0.06
    vm
    0.06
    اون
    0.06
     bats
    0.06
     different
    0.06
     worker
    0.06
    Act Density 0.063%

    No Known Activations