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

    Neuronpedia

    INDEX
    Explanations

    Responsibility Principle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ሆን
    0.39
     respetar
    0.38
     carving
    0.36
     Maradona
    0.36
     mysteriously
    0.35
    ⁦
    0.35
     carvings
    0.35
     overshadow
    0.34
    phere
    0.34
    ளுடன்
    0.34
    POSITIVE LOGITS
    Question
    0.44
    CO
    0.41
    question
    0.40
    BUF
    0.39
    Determine
    0.39
    Proble
    0.39
    Вы
    0.37
    Rates
    0.37
    頁
    0.37
    Knowledge
    0.37
    Act Density 0.000%

    No Known Activations