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

    Neuronpedia

    INDEX
    Explanations

    concentration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Filtering
    -0.07
     minden
    -0.07
     insomnia
    -0.06
    .loadData
    -0.06
     каждый
    -0.06
    LIMIT
    -0.06
     Blonde
    -0.06
    또
    -0.06
    Đây
    -0.06
     Mod
    -0.06
    POSITIVE LOGITS
     Ton
    0.06
    -touch
    0.06
     LOCATION
    0.06
     annot
    0.06
     voltage
    0.06
     Senator
    0.06
     Senators
    0.06
    fb
    0.06
    uvian
    0.05
     scopes
    0.05
    Act Density 0.001%

    No Known Activations