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

    Neuronpedia

    INDEX
    Explanations

    "about"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     olarak
    0.38
    లుగా
    0.37
    ட்ட
    0.35
     lainnya
    0.35
    க்காக
    0.35
    cima
    0.35
    ק
    0.34
     হিসেবে
    0.33
    лим
    0.33
    Blockchain
    0.33
    POSITIVE LOGITS
     الاقوامی
    0.37
     заболевания
    0.37
     médicale
    0.37
    textepsilon
    0.37
     dissatisfied
    0.36
    သည်
    0.36
    ยะ
    0.36
     anxieties
    0.36
     miasta
    0.36
     även
    0.35
    Act Density 0.006%

    No Known Activations