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

    Neuronpedia

    INDEX
    Explanations

    Economic/financial statistics and percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gear
    -0.07
    kos
    -0.06
    ướ
    -0.06
     Wong
    -0.06
     Gear
    -0.06
    九
    -0.06
     pathlib
    -0.06
     oldu
    -0.06
     ağaç
    -0.06
    abbage
    -0.06
    POSITIVE LOGITS
    posing
    0.08
    /off
    0.07
    (INT
    0.07
    masked
    0.06
    ddie
    0.06
     ）
    0.06
    (Operation
    0.06
    ricao
    0.06
     ví
    0.06
    Tick
    0.06
    Act Density 0.024%

    No Known Activations