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

    Neuronpedia

    INDEX
    Explanations

    argument help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aneity
    0.40
     syukur
    0.39
     Worship
    0.39
    ='')
    0.38
    ='',
    0.38
    基本的に
    0.36
     onus
    0.36
     змо
    0.35
     otomatis
    0.35
    દિવસ
    0.35
    POSITIVE LOGITS
     помощь
    0.38
     ayuda
    0.37
    帮助
    0.36
     πι
    0.36
     النار
    0.35
     help
    0.35
     hjäl
    0.35
    imensional
    0.34
     المل
    0.34
     weil
    0.34
    Act Density 0.001%

    No Known Activations