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

    Neuronpedia

    INDEX
    Explanations

    Racing starts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contractual
    -0.07
    気に入
    -0.07
    ekl
    -0.07
    	tree
    -0.06
     joke
    -0.06
     program
    -0.06
    ぅ
    -0.06
     receptors
    -0.06
     books
    -0.06
    	fields
    -0.06
    POSITIVE LOGITS
    ナ
    0.07
    ных
    0.06
    ์ก
    0.06
    露
    0.06
    .localtime
    0.06
     WI
    0.06
     ')
    0.06
    IFE
    0.06
     آلة
    0.06
                    
↵
    0.06
    Act Density 0.003%

    No Known Activations