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

    Neuronpedia

    INDEX
    Explanations

    say

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dados
    -0.07
     model
    -0.07
    /features
    -0.07
     habitat
    -0.07
    ása
    -0.07
    nero
    -0.06
    M
    -0.06
     saúde
    -0.06
     предпол
    -0.06
    σμό
    -0.06
    POSITIVE LOGITS
     SAY
    0.07
    激
    0.07
    	Server
    0.06
    earing
    0.06
    /')↵
    0.06
    .NEW
    0.06
    sburgh
    0.06
     iy
    0.06
    that
    0.06
     sä
    0.06
    Act Density 0.026%

    No Known Activations