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

    Neuronpedia

    INDEX
    Explanations

    living

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Dispatch
    -0.07
     Για
    -0.07
    .MATCH
    -0.06
    ffff
    -0.06
     pos
    -0.06
    。。↵↵
    -0.06
     taskId
    -0.06
     gradu
    -0.06
    >())
    -0.06
    .overflow
    -0.06
    POSITIVE LOGITS
     inadvert
    0.06
    476
    0.06
    े,
    0.06
    cmc
    0.06
     лю
    0.06
    anguages
    0.06
     Απ
    0.06
    lep
    0.06
    izo
    0.06
     memor
    0.06
    Act Density 0.001%

    No Known Activations