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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tree
    -0.06
    Cad
    -0.06
    quot
    -0.06
     rast
    -0.06
    pickup
    -0.06
    lists
    -0.06
     آق
    -0.06
    -sup
    -0.06
    朝
    -0.06
    viewModel
    -0.06
    POSITIVE LOGITS
    ạp
    0.07
    한국
    0.07
     Cf
    0.06
     한국
    0.06
     Postal
    0.06
     throwable
    0.06
     Fashion
    0.06
    .Here
    0.06
     가격
    0.06
     ड
    0.06
    Act Density 0.003%

    No Known Activations