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

    Neuronpedia

    INDEX
    Explanations

    declaration and document sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urale
    0.40
    MouseEnter
    0.39
     methodology
    0.39
    emo
    0.38
     prépar
    0.37
    Section
    0.37
     ancest
    0.37
     xiii
    0.37
    coord
    0.37
    onis
    0.37
    POSITIVE LOGITS
     Declaration
    0.64
     declaration
    0.63
    Declaration
    0.62
     declarations
    0.61
     déclaration
    0.55
    声明
    0.52
     ABSTRACT
    0.51
    declaration
    0.51
    宣言
    0.50
     declaración
    0.49
    Act Density 0.003%

    No Known Activations