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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to lessons learned from experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    relating to models, lessons, and inspiration

    np_acts-logits-general · gemini-2.0-flash

    inspiration, role models, lessons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.75
    URIComponent
    -0.70
    UserScript
    -0.68
    ArgsConstructor
    -0.65
    ValueGeneration
    -0.65
    seamnă
    -0.61
    ScopeManager
    -0.60
    ंदीखरीदारी
    -0.60
    __':
    -0.59
    nonatomic
    -0.58
    POSITIVE LOGITS
     lessons
    0.85
     Lessons
    0.79
     exemplar
    0.78
     lesson
    0.78
     Vorbild
    0.76
     lecciones
    0.72
     inspire
    0.72
    Lessons
    0.72
     example
    0.70
     model
    0.68
    Act Density 0.197%

    No Known Activations