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

    Neuronpedia

    INDEX
    Explanations

    basic python 3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Adaptation
    0.49
     adaption
    0.48
     adaptation
    0.45
     nauczyc
    0.42
     professeurs
    0.42
    宻
    0.41
     لات
    0.41
     lineColor
    0.41
     Instructor
    0.40
     לכ
    0.40
    POSITIVE LOGITS
     базо
    0.58
     basic
    0.56
    basic
    0.55
     básicos
    0.55
     basics
    0.51
     básicas
    0.51
    concepts
    0.51
    Concepts
    0.50
     básica
    0.49
    基本
    0.49
    Act Density 0.001%

    No Known Activations