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

    Neuronpedia

    INDEX
    Explanations

    Copyright

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Esk
    -0.07
     restriction
    -0.07
     apparent
    -0.07
     risking
    -0.07
     regression
    -0.06
    KI
    -0.06
    骄
    -0.06
     Escort
    -0.06
    .e
    -0.06
    	await
    -0.06
    POSITIVE LOGITS
    dí
    0.07
    保密
    0.07
    *dt
    0.07
    ACES
    0.06
    맸
    0.06
    กฎหมาย
    0.06
    通车
    0.06
    מוזיקה
    0.06
    sample
    0.06
    -under
    0.06
    Act Density 0.010%

    No Known Activations