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

    Neuronpedia

    INDEX
    Explanations

    table dividers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أم
    -0.07
    Baseline
    -0.07
     الحكوم
    -0.07
    펌
    -0.07
    的经典
    -0.07
    /session
    -0.07
    _export
    -0.07
    CMP
    -0.07
    กว
    -0.06
    こん
    -0.06
    POSITIVE LOGITS
    waiting
    0.07
    焘
    0.07
     countryCode
    0.07
     rarity
    0.06
     attaches
    0.06
     ruby
    0.06
    ril
    0.06
    rades
    0.06
    stripe
    0.06
     raj
    0.06
    Act Density 0.002%

    No Known Activations