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

    Neuronpedia

    INDEX
    Explanations

    Best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (nil
    -0.07
    failed
    -0.07
    	JLabel
    -0.07
    torch
    -0.07
    .LoggerFactory
    -0.07
    ovic
    -0.07
    üle
    -0.07
    \Route
    -0.07
     Dota
    -0.06
     Seller
    -0.06
    POSITIVE LOGITS
    /banner
    0.07
    ์น
    0.07
     α
    0.06
    ुभव
    0.06
    ################
    0.06
    وله
    0.06
     shall
    0.06
     больш
    0.06
    保护
    0.06
     trajectories
    0.06
    Act Density 0.119%

    No Known Activations