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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     деклара
    -0.09
     Declare
    -0.09
    declare
    -0.08
     ಕಲ
    -0.08
     declarations
    -0.08
     ঘোষণা
    -0.08
    Declaration
    -0.08
     പ്രഖ്യാപ
    -0.08
     déclaration
    -0.08
     ঘোষ
    -0.08
    POSITIVE LOGITS
     refers
    0.09
     referring
    0.08
     (?)
    0.08
     acronym
    0.08
    алаш
    0.08
     buds
    0.08
     PIN
    0.08
     abbreviation
    0.07
    poi
    0.07
    Poi
    0.07
    Act Density 0.060%

    No Known Activations