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

    Neuronpedia

    INDEX
    Explanations

    generating, teaching, missing, coming, compatible, lost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تأثير
    0.48
     überprüfen
    0.45
     başvur
    0.43
     etkisi
    0.42
     awal
    0.42
     arbet
    0.42
     allere
    0.42
     gewährleisten
    0.42
     بدأ
    0.42
     previstas
    0.42
    POSITIVE LOGITS
    র
    0.47
     Toma
    0.45
     Там
    0.43
     місце
    0.43
    ৌ
    0.43
     local
    0.41
     chemical
    0.40
     там
    0.40
    etí
    0.40
     smuggled
    0.40
    Act Density 0.048%

    No Known Activations