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

    Neuronpedia

    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Salt
    -0.06
    (an
    -0.06
    edException
    -0.06
     pee
    -0.06
    ze
    -0.06
    -opening
    -0.06
     sims
    -0.06
     lettuce
    -0.06
     mixer
    -0.06
     outdated
    -0.06
    POSITIVE LOGITS
    /sites
    0.07
     bedside
    0.07
    ạo
    0.07
    istributed
    0.06
     Without
    0.06
     volupt
    0.06
     artistic
    0.06
    regn
    0.06
    Anywhere
    0.06
    aln
    0.06
    Act Density 0.814%

    No Known Activations