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

    Neuronpedia

    INDEX
    Explanations

    employees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ));
    -0.07
    OffsetTable
    -0.06
    ν
    -0.06
     Zhang
    -0.06
    "On
    -0.06
    퓨
    -0.06
    olor
    -0.06
     вопрос
    -0.06
     různ
    -0.06
    нию
    -0.06
    POSITIVE LOGITS
     LIFE
    0.07
     concede
    0.07
    jabi
    0.06
     Spark
    0.06
    .notifyDataSetChanged
    0.06
     před
    0.06
    ple
    0.06
     Collective
    0.06
     stumbling
    0.06
    @Override
    0.06
    Act Density 0.000%

    No Known Activations