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

    Neuronpedia

    INDEX
    Explanations

    dates and holidays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     every
    0.55
     existing
    0.49
    _{
    0.47
     வாழ்வில்
    0.47
     end
    0.46
     WINTER
    0.46
    ividual
    0.46
     matrix
    0.46
     nutshell
    0.46
    धुनिक
    0.46
    POSITIVE LOGITS
     Национа
    0.73
     Remembrance
    0.67
    应当
    0.63
    ईद
    0.62
     Sunday
    0.62
     Boxing
    0.62
     Independence
    0.62
     Націона
    0.61
     Diwali
    0.61
     Тай
    0.61
    Act Density 0.021%

    No Known Activations