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

    Neuronpedia

    INDEX
    Explanations

    finding the value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    름
    1.00
     बल्
    0.91
    ان
    0.88
    title
    0.86
    om
    0.85
     सम्पर्क
    0.83
    디어
    0.83
    朧
    0.82
     Title
    0.81
    shall
    0.79
    POSITIVE LOGITS
     proposition
    1.08
     Proposition
    1.03
     gson
    1.00
     aggiunto
    0.99
    एशन
    0.98
    forKey
    0.97
     ajout
    0.95
     tambah
    0.92
    btnAdd
    0.91
     acrescent
    0.85
    Act Density 0.187%

    No Known Activations