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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ed
    -0.08
    .lists
    -0.07
     pencil
    -0.07
    剛
    -0.07
    <X
    -0.07
     Processes
    -0.06
    .music
    -0.06
    module
    -0.06
     Ed
    -0.06
    ati
    -0.06
    POSITIVE LOGITS
     macOS
    0.08
     Rolex
    0.07
    wins
    0.06
     assuming
    0.06
     iOS
    0.06
     lokale
    0.06
     досить
    0.06
     زن
    0.06
    parate
    0.06
     ipt
    0.06
    Act Density 0.245%

    No Known Activations