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

    Neuronpedia

    INDEX
    Explanations

    Catching someone walking in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilenames
    -0.07
    .setModel
    -0.07
    iatrics
    -0.07
     Guidelines
    -0.07
    Productos
    -0.07
    원의
    -0.06
    Leading
    -0.06
    top
    -0.06
    .worker
    -0.06
     Leading
    -0.06
    POSITIVE LOGITS
    Decode
    0.06
    銀
    0.06
     Nass
    0.06
     Boutique
    0.06
     CAST
    0.05
    -needed
    0.05
     Placement
    0.05
    -error
    0.05
     nevy
    0.05
                ↵
    0.05
    Act Density 0.027%

    No Known Activations