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

    Neuronpedia

    INDEX
    Explanations

    geometric shapes and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tofu
    0.73
    aporte
    0.73
     mlij
    0.70
     КП
    0.70
     buffet
    0.69
     পাওয়ার
    0.69
     ਨੇ
    0.68
    itaea
    0.67
     needs
    0.67
    Autowired
    0.67
    POSITIVE LOGITS
    মোট
    0.61
    かん
    0.58
     Federación
    0.55
    Thoughts
    0.51
    ੁੱ
    0.50
    我不
    0.50
    Focused
    0.50
    γχ
    0.50
     lawful
    0.50
    I
    0.50
    Act Density 0.081%

    No Known Activations