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

    Neuronpedia

    INDEX
    Explanations

    fundamental and basic concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     refugiados
    -0.72
    捍
    -0.71
     serpiente
    -0.70
    пыт
    -0.69
     asisti
    -0.68
     neuve
    -0.67
     respaldo
    -0.67
    ThemeProvider
    -0.66
    ା
    -0.66
    ouard
    -0.66
    POSITIVE LOGITS
     fundamental
    2.56
    fundamental
    2.17
    Fundamental
    1.92
     basic
    1.90
     central
    1.87
     core
    1.84
    基本
    1.80
     podstaw
    1.76
     key
    1.73
     Fundamental
    1.73
    Act Density 0.080%

    No Known Activations