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

    Neuronpedia

    INDEX
    Explanations

    Qualification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -reviewed
    -0.07
    .con
    -0.06
    .AlertDialog
    -0.06
     @"↵
    -0.06
     Kanun
    -0.06
     sıra
    -0.06
     Ιω
    -0.06
     +-
    -0.06
     çerçev
    -0.06
     dome
    -0.06
    POSITIVE LOGITS
    Greg
    0.07
     intox
    0.07
    qualified
    0.07
     cheating
    0.06
     Greg
    0.06
     Multi
    0.06
     retr
    0.06
    launch
    0.06
    athan
    0.06
     genç
    0.06
    Act Density 0.002%

    No Known Activations