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

    Neuronpedia

    INDEX
    Explanations

    variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Georgian
    -0.08
     Caribe
    -0.08
     partit
    -0.08
     typo
    -0.07
     �
    -0.07
     Arctic
    -0.07
     കോണ്
    -0.07
    idus
    -0.07
     పడ
    -0.07
     জম
    -0.07
    POSITIVE LOGITS
     변수
    0.15
    变量
    0.15
     variables
    0.15
    Variables
    0.13
    variables
    0.13
     Variables
    0.13
    _variables
    0.12
     correlations
    0.11
    .variables
    0.11
     VARIABLES
    0.11
    Act Density 0.019%

    No Known Activations