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

    Neuronpedia

    INDEX
    Explanations

    check

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الف
    -0.07
     dedicate
    -0.07
    analysis
    -0.07
    简历
    -0.07
     Louisville
    -0.07
     admir
    -0.07
    アイ
    -0.07
     annotated
    -0.07
     Argentina
    -0.07
     impoverished
    -0.07
    POSITIVE LOGITS
     progressBar
    0.07
    	border
    0.07
     Operator
    0.07
    ister
    0.06
    ictions
    0.06
    	fd
    0.06
    	function
    0.06
    部部长
    0.06
    jak
    0.06
    -system
    0.06
    Act Density 0.009%

    No Known Activations