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

    Neuronpedia

    INDEX
    Explanations

    yearly frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Será
    0.50
    ӓ
    0.47
     Bao
    0.45
     avrà
    0.45
     rápido
    0.44
    sap
    0.43
     rapide
    0.43
     transp
    0.42
    డ్‌
    0.42
     potrà
    0.41
    POSITIVE LOGITS
    每年
    1.67
    毎年
    1.63
     annually
    1.62
     yearly
    1.42
     annual
    1.38
     jährlich
    1.36
     еже
    1.31
     anual
    1.23
    毎回
    1.21
     annuel
    1.20
    Act Density 0.483%

    No Known Activations