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

    Neuronpedia

    INDEX
    Explanations

    awards ceremonies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nivel
    -0.06
     Pac
    -0.06
     pac
    -0.06
     trib
    -0.06
    江
    -0.06
     eigen
    -0.05
    ark
    -0.05
     ow
    -0.05
     Penn
    -0.05
     Finland
    -0.05
    POSITIVE LOGITS
    selectedIndex
    0.07
    igslist
    0.07
    /close
    0.07
    CFG
    0.06
    .didReceiveMemoryWarning
    0.06
     Customize
    0.06
    reservation
    0.06
    (identity
    0.06
    **↵
    0.06
     ^=
    0.06
    Act Density 0.087%

    No Known Activations