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

    Neuronpedia

    INDEX
    Explanations

    understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ヨ
    -0.06
    =event
    -0.06
     Column
    -0.06
     Woj
    -0.06
     números
    -0.06
    "a
    -0.06
     namespace
    -0.06
     kaz
    -0.06
     MONEY
    -0.06
    lyphicon
    -0.06
    POSITIVE LOGITS
     understanding
    0.16
     Understanding
    0.12
     awareness
    0.08
     mastery
    0.08
    Understanding
    0.07
     Awareness
    0.07
     Handling
    0.07
    .stage
    0.07
    体系
    0.07
     Ont
    0.07
    Act Density 0.019%

    No Known Activations