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

    Neuronpedia

    INDEX
    Explanations

    ware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     advancements
    -0.07
     Britain
    -0.07
    503
    -0.07
     economics
    -0.07
    states
    -0.07
     сообщ
    -0.06
    LIN
    -0.06
     Robertson
    -0.06
     Economics
    -0.06
     ім
    -0.06
    POSITIVE LOGITS
    camp
    0.08
    pressive
    0.06
    assy
    0.06
    ervention
    0.06
     �
    0.06
     pale
    0.06
     Results
    0.06
    _management
    0.06
    RESULTS
    0.06
    tridges
    0.06
    Act Density 0.009%

    No Known Activations