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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aln
    -0.06
    ถนน
    -0.06
     medals
    -0.06
    ali
    -0.06
     bez
    -0.06
    retch
    -0.06
    ebin
    -0.06
     memor
    -0.06
     roma
    -0.06
     mé
    -0.05
    POSITIVE LOGITS
     <=>
    0.07
     compassionate
    0.07
    ριος
    0.07
    	Dim
    0.07
    ><!--
    0.07
    '↵↵↵
    0.06
     енерг
    0.06
     KEY
    0.06
     ذات
    0.06
     نقشه
    0.06
    Act Density 0.001%

    No Known Activations