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

    Neuronpedia

    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Amanda
    -0.06
    들도
    -0.06
    věř
    -0.06
     التعليم
    -0.06
     Brah
    -0.06
     Paleo
    -0.06
    _energy
    -0.06
    Middle
    -0.06
     MDB
    -0.06
     Lage
    -0.06
    POSITIVE LOGITS
     celebrating
    0.07
     dense
    0.06
     flew
    0.06
    Error
    0.06
    NIC
    0.06
    (find
    0.06
    ovies
    0.06
    ibrary
    0.06
    color
    0.06
    gebn
    0.06
    Act Density 0.055%

    No Known Activations