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

    Neuronpedia

    INDEX
    Explanations

    scientific and mathematical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proper
    0.68
     b
    0.65
     some
    0.64
     right
    0.64
     a
    0.63
     create
    0.62
     all
    0.62
     adding
    0.62
     certain
    0.62
     local
    0.61
    POSITIVE LOGITS
    Pyrazole
    0.87
    Setelah
    0.81
    Jumlah
    0.81
    LuaPush
    0.80
    Ảnh
    0.80
    Pedido
    0.79
    Makanan
    0.79
    Coins
    0.79
     Matemática
    0.78
    UIntValue
    0.78
    Act Density 0.001%

    No Known Activations