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

    Neuronpedia

    INDEX
    Explanations

    square

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incredibly
    -0.08
     Babylon
    -0.08
     �
    -0.08
    ffects
    -0.08
    �
    -0.08
    ೃದ
    -0.08
     righteousness
    -0.08
    -acre
    -0.08
     fertility
    -0.08
     splitted
    -0.08
    POSITIVE LOGITS
     requirements
    0.08
     పర
    0.08
     Container
    0.08
     hosts
    0.08
     enclosing
    0.08
    Requirement
    0.07
     आवश्यकता
    0.07
    Requirements
    0.07
    requirements
    0.07
    .host
    0.07
    Act Density 0.043%

    No Known Activations