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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ersive
    -0.07
    plex
    -0.06
    ING
    -0.06
    ी-
    -0.06
     clear
    -0.06
    -p
    -0.06
     modern
    -0.06
    carbon
    -0.06
     THIS
    -0.06
     volunteers
    -0.06
    POSITIVE LOGITS
     denomin
    0.07
    Seq
    0.07
    achte
    0.07
     errone
    0.07
     Finally
    0.06
     listings
    0.06
    .ylabel
    0.06
     Clone
    0.06
    .JFrame
    0.06
    ún
    0.06
    Act Density 0.000%

    No Known Activations