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

    Neuronpedia

    INDEX
    Explanations

    location and date separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spool
    0.52
     alman
    0.47
     också
    0.45
     posi
    0.45
    насти
    0.45
    也会
    0.45
     sath
    0.44
     static
    0.43
     dicho
    0.43
     relatable
    0.43
    POSITIVE LOGITS
     The
    0.59
     Seorang
    0.59
    The
    0.56
     Ві
    0.53
    Сегодня
    0.53
     આજે
    0.50
     येथील
    0.49
     Despite
    0.49
    Three
    0.49
    Ä
    0.49
    Act Density 0.004%

    No Known Activations