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

    Neuronpedia

    INDEX
    Explanations

    searching for things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nuns
    0.40
     дальше
    0.40
     кажется
    0.40
     аба
    0.39
     सरकारी
    0.38
     laranja
    0.38
     जोशी
    0.37
     thổi
    0.37
    ПА
    0.37
    ानगर
    0.36
    POSITIVE LOGITS
     visited
    0.44
     besuchen
    0.41
     besucht
    0.41
    note
    0.39
    visited
    0.39
    Visited
    0.38
     besuchte
    0.38
    casualties
    0.37
     attractions
    0.36
     মূল্যবান
    0.36
    Act Density 0.001%

    No Known Activations