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

    Neuronpedia

    INDEX
    Explanations

    welcome the opportunity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     名
    0.67
     compone
    0.67
    esorios
    0.66
    rma
    0.66
     names
    0.64
     nomes
    0.64
     нама
    0.63
     remont
    0.63
    ılığı
    0.63
    బో
    0.63
    POSITIVE LOGITS
     new
    1.23
     neuen
    1.11
    new
    1.07
     новый
    1.05
     নতুন
    1.05
     новые
    1.05
     nuove
    1.03
     baru
    1.01
     новых
    1.00
     nieuwe
    0.99
    Act Density 0.017%

    No Known Activations