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

    Neuronpedia

    INDEX
    Explanations

    Counterfeit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     touchdowns
    -0.06
     newfound
    -0.06
     Facility
    -0.06
     exams
    -0.06
    _rec
    -0.06
     взрос
    -0.06
     facility
    -0.06
     Glory
    -0.06
     운영
    -0.06
    śmy
    -0.06
    POSITIVE LOGITS
     Shoes
    0.07
     Catalan
    0.06
    هر
    0.06
    inside
    0.06
    (#)
    0.06
     le
    0.06
    	cerr
    0.06
     Supplement
    0.06
    environment
    0.06
    평
    0.06
    Act Density 0.004%

    No Known Activations