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

    Neuronpedia

    INDEX
    Explanations

    swiftui previews and code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يت
    1.61
     thiab
    1.59
    και
    1.58
    え
    1.52
     Unido
    1.51
    1.48
     أيضاً
    1.47
    cope
    1.45
    ystem
    1.43
    Pedido
    1.43
    POSITIVE LOGITS
    ers
    1.62
    IA
    1.62
    age
    1.59
    тран
    1.53
     Fian
    1.50
    ERS
    1.47
    speople
    1.45
    !\!\
    1.45
    DR
    1.40
     Dessa
    1.39
    Act Density 0.000%

    No Known Activations