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

    Neuronpedia

    INDEX
    Explanations

    expense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cán
    -0.07
     Aur
    -0.07
    ait
    -0.07
     coloured
    -0.07
     Mand
    -0.07
     hled
    -0.07
    洞
    -0.07
     luder
    -0.06
     CZ
    -0.06
     NAT
    -0.06
    POSITIVE LOGITS
     expenses
    0.18
     expense
    0.16
     Expenses
    0.15
     Expense
    0.14
    expenses
    0.12
    expense
    0.11
    Expense
    0.11
    �
    0.08
    енс
    0.07
    panse
    0.07
    Act Density 0.004%

    No Known Activations