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

    Neuronpedia

    INDEX
    Explanations

    Narratives/Events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (character
    -0.08
     roles
    -0.07
     Industry
    -0.07
    ством
    -0.07
     rewards
    -0.07
     cables
    -0.07
    Liquid
    -0.07
     rewarded
    -0.06
    -enabled
    -0.06
     share
    -0.06
    POSITIVE LOGITS
    Vals
    0.06
     Τζ
    0.06
     Пол
    0.06
     warmed
    0.06
    ！！
    0.06
    .addProperty
    0.06
    .GetMapping
    0.06
     USAGE
    0.06
    .until
    0.06
    abilmek
    0.06
    Act Density 0.059%

    No Known Activations