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

    Neuronpedia

    INDEX
    Explanations

    Artificial intelligence/robots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    miss
    -0.08
    institution
    -0.07
    意
    -0.06
    react
    -0.06
    iyesi
    -0.06
    Truth
    -0.06
    "When
    -0.06
     Granny
    -0.06
     Romania
    -0.06
    義
    -0.06
    POSITIVE LOGITS
    OCUMENT
    0.07
    pending
    0.06
    ero
    0.06
    entials
    0.06
     всп
    0.06
     APC
    0.06
     currents
    0.06
    ar
    0.06
    .spatial
    0.06
     Accounting
    0.06
    Act Density 0.013%

    No Known Activations