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

    Neuronpedia

    INDEX
    Explanations

    penetration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DISPATCH
    -0.07
    Mayor
    -0.06
    _miss
    -0.06
    ули
    -0.06
    mem
    -0.06
     ülkemiz
    -0.06
    Usage
    -0.06
    Be
    -0.06
     GURL
    -0.06
    Empty
    -0.06
    POSITIVE LOGITS
     contracting
    0.07
     Chains
    0.07
     ages
    0.06
     cane
    0.06
    (ids
    0.06
    
    0.06
     detections
    0.06
     hypers
    0.06
     분석
    0.06
     Prel
    0.06
    Act Density 0.010%

    No Known Activations