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

    Neuronpedia

    INDEX
    Explanations

    say period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Utilities
    -0.07
    consin
    -0.07
     eget
    -0.06
    (Point
    -0.06
    Β
    -0.06
    .windows
    -0.06
    ishing
    -0.06
     surface
    -0.06
    signup
    -0.06
    ента
    -0.06
    POSITIVE LOGITS
     *))
    0.07
     田
    0.07
     TM
    0.06
     %@",
    0.06
     ustanov
    0.06
    .PageSize
    0.06
     bund
    0.06
     Bolt
    0.06
     pä
    0.06
     {!
    0.06
    Act Density 0.085%

    No Known Activations