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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    уб
    -0.08
    אוטובוס
    -0.07
     coupling
    -0.07
    <>(
    -0.07
    븐
    -0.07
     Occupational
    -0.07
    .")
    -0.07
    (inputStream
    -0.07
    ឥ
    -0.07
    graphql
    -0.07
    POSITIVE LOGITS
    	source
    0.07
     hạn
    0.07
    ®
    0.06
     mirac
    0.06
     dạng
    0.06
    ˔
    0.06
    会在
    0.06
     fod
    0.06
    	cont
    0.06
     fica
    0.06
    Act Density 0.057%

    No Known Activations