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

    Neuronpedia

    INDEX
    Explanations

    tax law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hands
    -0.06
    ových
    -0.06
     Manufacturing
    -0.06
     cast
    -0.06
    Jeff
    -0.06
    신
    -0.06
     est
    -0.06
    暮
    -0.06
     vợ
    -0.06
    Alex
    -0.06
    POSITIVE LOGITS
    _Total
    0.07
    erved
    0.06
     století
    0.06
    ได
    0.06
    ovation
    0.06
    creates
    0.06
     Boris
    0.06
    ταν
    0.06
     dropout
    0.06
     invoice
    0.06
    Act Density 0.017%

    No Known Activations