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

    Neuronpedia

    INDEX
    Explanations

    code debugging/logging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	intent
    -0.08
    []>
    -0.06
     spielen
    -0.06
    -0.06
     agent
    -0.06
     phân
    -0.06
     parseInt
    -0.06
    .KeyEvent
    -0.06
    XXX
    -0.06
     *}↵↵
    -0.06
    POSITIVE LOGITS
     apple
    0.07
    면서
    0.06
    apolis
    0.06
     minden
    0.06
     cheering
    0.06
    最
    0.06
    CEEDED
    0.06
    λλην
    0.06
     resurrection
    0.06
     rim
    0.06
    Act Density 0.012%

    No Known Activations