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

    Neuronpedia

    INDEX
    Explanations

    agreement or decisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cellFor
    -0.07
     doom
    -0.07
    Dt
    -0.07
     Strength
    -0.06
     rng
    -0.06
     Stamina
    -0.06
    .twitch
    -0.06
     случае
    -0.06
    ibern
    -0.06
     Raid
    -0.06
    POSITIVE LOGITS
     khối
    0.07
    -secret
    0.07
     sve
    0.06
     luaL
    0.06
     Açık
    0.06
    ább
    0.06
     образования
    0.06
    อาหาร
    0.06
     correction
    0.06
     مختصات
    0.06
    Act Density 0.002%

    No Known Activations