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

    Neuronpedia

    INDEX
    Explanations

    explaining description, purpose, or claim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embodiments
    0.49
     achievements
    0.46
     frases
    0.45
     accomplishments
    0.44
     பணிகள்
    0.44
     QUESTIONS
    0.44
     проекты
    0.44
     projects
    0.44
     proyectos
    0.44
     நடவடிக்கைகள்
    0.43
    POSITIVE LOGITS
     idea
    0.70
     concept
    0.70
     notion
    0.68
    concept
    0.63
     phenomenon
    0.59
     concetto
    0.59
     issue
    0.59
     principle
    0.57
    idea
    0.55
     constraint
    0.54
    Act Density 0.235%

    No Known Activations