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

    Neuronpedia

    INDEX
    Explanations

    explaining "what is"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     futuras
    0.71
    あとは
    0.66
     examples
    0.65
     ejemplos
    0.61
    Examples
    0.60
    recipes
    0.60
     recipes
    0.59
    Recipes
    0.59
     Examples
    0.58
     exemplos
    0.58
    POSITIVE LOGITS
     Overview
    2.58
    Overview
    2.55
     overview
    2.40
     Background
    2.38
     background
    2.37
    Background
    2.30
    overview
    2.23
    背景
    2.13
    概要
    2.11
    background
    2.01
    Act Density 0.973%

    No Known Activations