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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Congrats
    -0.13
     Congratulations
    -0.13
     �
    -0.12
     congratulations
    -0.12
    Congrats
    -0.12
    ，今年
    -0.12
    今年
    -0.12
    😂
    -0.12
    �
    -0.12
     newbie
    -0.12
    POSITIVE LOGITS
     Methods
    0.15
    Methods
    0.14
     Functions
    0.14
    Structures
    0.14
    Characteristics
    0.14
     často
    0.14
    Variants
    0.14
    Types
    0.14
    Definitions
    0.14
     Often
    0.14
    Act Density 0.187%

    No Known Activations