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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    çek
    -0.06
     misdemeanor
    -0.06
    Checkpoint
    -0.06
     WriteLine
    -0.06
     DO
    -0.06
     upheld
    -0.06
     �
    -0.05
     File
    -0.05
     nineteenth
    -0.05
    including
    -0.05
    POSITIVE LOGITS
     Afghanistan
    0.10
     Ireland
    0.09
     India
    0.08
     Vietnam
    0.08
     Malaysia
    0.08
     America
    0.08
     France
    0.08
     Russia
    0.08
     China
    0.08
     Thailand
    0.08
    Act Density 0.184%

    No Known Activations