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

    Neuronpedia

    INDEX
    Explanations

    Society

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     booster
    -0.07
    abetes
    -0.07
    _);↵↵
    -0.07
     blue
    -0.06
     funnel
    -0.06
     expulsion
    -0.06
     Install
    -0.06
    /wait
    -0.06
     ());↵
    -0.06
    _big
    -0.06
    POSITIVE LOGITS
     Society
    0.10
     society
    0.08
    Guild
    0.07
    SOC
    0.07
     Guild
    0.07
     gossip
    0.07
    /entities
    0.07
     surviving
    0.07
     ModelState
    0.07
     societies
    0.07
    Act Density 0.026%

    No Known Activations