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

    Neuronpedia

    INDEX
    Explanations

    common prefix or example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    covid
    0.31
    นักงาน
    0.28
    乡村
    0.28
    Từ
    0.28
     Prefeitura
    0.27
    ková
    0.27
    anoi
    0.27
    ेट्टी
    0.27
    Planner
    0.27
    astra
    0.27
    POSITIVE LOGITS
     ہوسک
    0.28
     adherents
    0.27
     Ausdruck
    0.26
     inequality
    0.25
     alkalies
    0.25
     acidosis
    0.25
     மிக
    0.25
     wenn
    0.25
    becomes
    0.25
     manchmal
    0.24
    Act Density 0.093%

    No Known Activations