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

    Neuronpedia

    INDEX
    Explanations

    .g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -team
    -0.07
    NULL
    -0.07
    ása
    -0.07
     향
    -0.07
    orris
    -0.07
    adeon
    -0.06
    よね
    -0.06
     boys
    -0.06
     WAN
    -0.06
    	If
    -0.06
    POSITIVE LOGITS
    ground
    0.07
    /'+
    0.06
    μενο
    0.06
    libc
    0.06
     Ibn
    0.06
     Craig
    0.06
    (bodyParser
    0.06
     nextPage
    0.06
     Nearly
    0.06
     Cr
    0.06
    Act Density 0.018%

    No Known Activations